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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinion or personal sentiment

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

    Follows personal opinions or requests

    np_acts-logits-general · gemini-2.0-flash

    expressing certainty or opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ább
    -0.36
     aislado
    -0.36
    SE
    -0.35
     virtud
    -0.35
     isoliert
    -0.35
     aislada
    -0.34
    se
    -0.32
     aislados
    -0.32
     grises
    -0.32
     iaitu
    -0.32
    POSITIVE LOGITS
     ModelExpression
    0.65
     MenuView
    0.65
     Савезне
    0.55
     CreateTagHelper
    0.54
    发表于
    0.53
     فريبيس
    0.53
    Personendaten
    0.52
    LookAnd
    0.51
    OGND
    0.51
    RegressionTest
    0.50
    Act Density 0.186%

    No Known Activations