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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

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

    code blocks with parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.51
    ↵
    -0.49
     rain
    -0.40
    ↵↵
    -0.40
     
    -0.39
     land
    -0.35
     past
    -0.34
     confirmed
    -0.34
    …
    -0.33
     rent
    -0.33
    POSITIVE LOGITS
    EndContext
    0.88
    原始内容存档于
    0.83
     CreateTagHelper
    0.82
    uxxxx
    0.81
    ValueStyle
    0.78
    Datuak
    0.76
    Tikang
    0.75
    tvguidetime
    0.74
    AnimationsModule
    0.72
    +:+
    0.72
    Act Density 0.115%

    No Known Activations