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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     методи
    -0.06
    Culture
    -0.06
    telephone
    -0.06
    Hillary
    -0.06
    Been
    -0.06
    xFFFFFFFF
    -0.06
    tatus
    -0.06
    centroid
    -0.06
    ('_',
    -0.06
     Suppress
    -0.06
    POSITIVE LOGITS
    打
    0.07
     global
    0.07
     Finn
    0.07
    �
    0.07
    公
    0.06
     victories
    0.06
     thị
    0.06
     Ride
    0.06
     exclus
    0.06
     Low
    0.06
    Act Density 0.036%

    No Known Activations