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

    Neuronpedia

    INDEX
    Explanations

    fatty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     redefine
    -0.06
    upal
    -0.06
     praised
    -0.06
    ěti
    -0.06
    」の
    -0.06
    々
    -0.06
    YPD
    -0.06
    시아
    -0.06
     permit
    -0.06
    amente
    -0.06
    POSITIVE LOGITS
    .quant
    0.07
    /em
    0.07
     or
    0.06
     кост
    0.06
    RESP
    0.06
    _Att
    0.06
     appreciated
    0.06
    (logging
    0.06
    openid
    0.06
    /body
    0.06
    Act Density 0.003%

    No Known Activations