Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives related to character traits and qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following hyphenated adjectives

    np_acts-logits-general · gemini-2.0-flash

    compound adjectives and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.72
     leaſt
    -0.70
    دانشنامهٔ
    -0.69
    oa̍t
    -0.67
     سكانية
    -0.67
    JsonHelper
    -0.66
     kasarigan
    -0.66
    ruptedException
    -0.64
     JSONException
    -0.64
    yntaxException
    -0.64
    POSITIVE LOGITS
     minded
    1.22
    minded
    1.09
    hearted
    0.91
    headed
    0.85
     hearted
    0.82
    handed
    0.79
     headed
    0.76
     handed
    0.72
    footed
    0.72
     willed
    0.72
    Act Density 0.169%

    No Known Activations