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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lush
    -0.08
    нич
    -0.07
    _ERR
    -0.07
    Running
    -0.06
    _MISC
    -0.06
    .IsNullOr
    -0.06
    (di
    -0.06
    春节
    -0.06
     tight
    -0.06
     SEEK
    -0.06
    POSITIVE LOGITS
    intérieur
    0.07
    uetype
    0.07
    ｧ
    0.07
    Numeric
    0.07
    說明
    0.07
     feminine
    0.07
     форме
    0.06
     certainly
    0.06
    _instructions
    0.06
     Inspir
    0.06
    Act Density 0.011%

    No Known Activations