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

    Neuronpedia

    INDEX
    Explanations

    Modus Ponens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.94
    to
    0.80
     یا
    0.78
    '
    0.77
    то
    0.75
    мо
    0.70
     که
    0.69
     світу
    0.69
     بین
    0.68
    on
    0.67
    POSITIVE LOGITS
     C
    0.67
     I
    0.63
     M
    0.61
    pping
    0.60
     Dieser
    0.59
     L
    0.57
    輿
    0.55
     NPM
    0.55
     MSP
    0.54
     Zanz
    0.54
    Act Density 0.006%

    No Known Activations