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

    Neuronpedia

    INDEX
    Explanations

    negotiation or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Statement
    0.55
    at
    0.53
    是
    0.52
    ok
    0.47
    ，
    0.47
     Facility
    0.46
     completes
    0.45
    jsk
    0.45
    L
    0.44
    。
    0.44
    POSITIVE LOGITS
    slidesPer
    0.52
    AMINATION
    0.50
     اُ
    0.49
    ISER
    0.49
    ROTTLE
    0.49
     رجال
    0.48
    クレジットカード
    0.47
     sciatica
    0.47
    шения
    0.47
     alojamiento
    0.47
    Act Density 0.000%

    No Known Activations