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

    Neuronpedia

    INDEX
    Explanations

    phrases that express perception or interpretation of things

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

    viewed as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⇥
    -0.35
    \"\
    -0.34
    help
    -0.34
     изу
    -0.33
     chiesto
    -0.32
    DOCTYPE
    -0.32
    redning
    -0.32
    sepeda
    -0.32
     arrep
    -0.31
    ResumeLayout
    -0.31
    POSITIVE LOGITS
    QMetaType
    0.67
     perceives
    0.64
     Regard
    0.63
     considers
    0.62
     regarded
    0.61
     considère
    0.60
     Considered
    0.60
     للمعارف
    0.58
     viewed
    0.58
     regard
    0.58
    Act Density 0.189%

    No Known Activations