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

    Neuronpedia

    INDEX
    Explanations

    the more the better

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拼
    -0.07
    グ
    -0.06
    /template
    -0.06
     फर
    -0.06
     trav
    -0.06
     Negative
    -0.06
     �
    -0.06
     eoqkrvldkf
    -0.06
     भर
    -0.06
     backButton
    -0.06
    POSITIVE LOGITS
    щё
    0.07
    .iloc
    0.07
    __(*
    0.06
     było
    0.06
     đ
    0.06
    /**/*.
    0.06
     Jose
    0.06
    661
    0.06
    ceso
    0.06
     maman
    0.06
    Act Density 0.005%

    No Known Activations