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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suc
    -0.07
    ครง
    -0.06
    _inter
    -0.06
    \Exceptions
    -0.06
     filtro
    -0.06
     circumstance
    -0.06
    Sharper
    -0.06
     Descriptor
    -0.06
     yere
    -0.06
    multipart
    -0.06
    POSITIVE LOGITS
     еп
    0.07
    ±n
    0.07
     امروز
    0.07
     explic
    0.06
    .sap
    0.06
    IDENT
    0.06
    .addEventListener
    0.06
    pictured
    0.06
     macOS
    0.06
    .Handle
    0.06
    Act Density 0.013%

    No Known Activations