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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tactics
    -0.07
    mode
    -0.06
     alloys
    -0.06
    _ln
    -0.06
     legitimacy
    -0.06
    CriticalSection
    -0.06
    еку
    -0.06
    .loadtxt
    -0.06
    \controllers
    -0.06
     algorithm
    -0.06
    POSITIVE LOGITS
     cott
    0.07
     dra
    0.06
    ONT
    0.06
     besch
    0.06
     fund
    0.06
    prepare
    0.06
     dahi
    0.06
    .cat
    0.06
     grö
    0.06
     sonrası
    0.06
    Act Density 0.002%

    No Known Activations