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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (predicate
    -0.07
    Sampling
    -0.07
     WriteLine
    -0.06
     pessim
    -0.06
    stood
    -0.06
     logout
    -0.06
     Rhino
    -0.06
     terrified
    -0.06
     Gina
    -0.06
    specialchars
    -0.06
    POSITIVE LOGITS
    ανά
    0.06
    　ヾ
    0.06
    saida
    0.06
     verdiği
    0.06
    _flashdata
    0.05
    omon
    0.05
    الم
    0.05
     explain
    0.05
    ету
    0.05
     licz
    0.05
    Act Density 0.053%

    No Known Activations