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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cow
    -0.07
    serialization
    -0.07
    notEmpty
    -0.06
    acct
    -0.06
     DataSet
    -0.06
     weiber
    -0.06
    Bat
    -0.06
    ;set
    -0.06
    /info
    -0.06
    _minor
    -0.06
    POSITIVE LOGITS
    нього
    0.07
     paperwork
    0.06
    matter
    0.06
    sou
    0.06
     retorno
    0.06
    _lstm
    0.06
    ButtonText
    0.06
     kom
    0.06
    Kom
    0.06
    _maximum
    0.06
    Act Density 0.005%

    No Known Activations