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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subpoena
    -0.07
    Ō
    -0.07
    felt
    -0.07
    _elems
    -0.07
     receber
    -0.07
    nyder
    -0.07
     rg
    -0.07
    enberg
    -0.07
    義務
    -0.07
     azi
    -0.07
    POSITIVE LOGITS
    àn
    0.07
    &);↵
    0.07
    ;/
    0.07
     jeśli
    0.07
    ="/">
    0.07
     rational
    0.07
    .meta
    0.07
    {}.
    0.07
    ................................
    0.07
     sürek
    0.06
    Act Density 0.003%

    No Known Activations