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

    Neuronpedia

    INDEX
    Explanations

    сек

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kelim
    -0.07
     getChild
    -0.07
     hậu
    -0.06
     voiture
    -0.06
     zipcode
    -0.06
    (rr
    -0.06
     geen
    -0.06
    (bc
    -0.06
    flater
    -0.06
    zeigen
    -0.06
    POSITIVE LOGITS
     кис
    0.07
    .VERTICAL
    0.07
     хви
    0.07
    ι
    0.06
    .Int
    0.06
     Lindsey
    0.06
     bachelor
    0.06
     #####
    0.06
     trainable
    0.06
    嘴
    0.06
    Act Density 0.003%

    No Known Activations