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

    Neuronpedia

    INDEX
    Explanations

    appropriate response in context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     С
    0.16
     without
    0.16
     К
    0.16
    랗
    0.16
     any
    0.16
     this
    0.16
    racting
    0.16
     betreff
    0.15
     বিচ
    0.15
     you
    0.15
    POSITIVE LOGITS
     exuber
    0.20
    នូវ
    0.20
     megaphone
    0.18
     antagonism
    0.18
     obsol
    0.18
     approach
    0.18
     porosity
    0.18
     nostalgia
    0.17
     overdose
    0.17
     ultimatum
    0.17
    Act Density 1.447%

    No Known Activations