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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     ADM
    -0.07
    _specs
    -0.06
     ruk
    -0.06
     Satan
    -0.06
     NAMES
    -0.06
     trouve
    -0.06
    анны
    -0.06
     ifstream
    -0.06
    Hand
    -0.06
    POSITIVE LOGITS
     lsp
    0.06
    ilecek
    0.06
     může
    0.06
     Owned
    0.06
    oralType
    0.06
     usar
    0.06
     Jays
    0.06
    .preventDefault
    0.06
    merged
    0.06
    regist
    0.06
    Act Density 0.005%

    No Known Activations