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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     melts
    -0.07
     вари
    -0.07
    iders
    -0.06
    resses
    -0.06
     verg
    -0.06
     vů
    -0.06
     sweat
    -0.06
     quoted
    -0.06
     وقت
    -0.06
     AppComponent
    -0.06
    POSITIVE LOGITS
     się
    0.07
    zahl
    0.07
    ै।↵↵
    0.06
    ิงหาคม
    0.06
    )(↵
    0.06
    (customer
    0.06
    ября
    0.06
    Delivery
    0.06
     참여
    0.06
    料無料
    0.06
    Act Density 0.000%

    No Known Activations