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

    Neuronpedia

    INDEX
    Explanations

    describing specific systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BET
    0.44
     посвя
    0.40
    PROCESSING
    0.40
     گوئی
    0.39
    блі
    0.39
     handen
    0.39
    GoObject
    0.39
    FAX
    0.39
    ^\
    0.38
     Quillen
    0.38
    POSITIVE LOGITS
    ),'
    0.43
    创建
    0.42
    ='
    0.41
    ერ
    0.38
    )+'
    0.38
    -->'
    0.38
     '+
    0.37
     militant
    0.36
    层的
    0.36
     +'
    0.36
    Act Density 0.000%

    No Known Activations