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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "';↵
    -0.06
     mais
    -0.06
    _B
    -0.06
     "))
    -0.06
     цим
    -0.06
    ('/')↵
    -0.06
    ax
    -0.06
    indre
    -0.06
     も
    -0.06
    patches
    -0.06
    POSITIVE LOGITS
    ок
    0.07
    sessions
    0.07
    оку
    0.07
    REMOVE
    0.06
     Wrestle
    0.06
    timeout
    0.06
     ".
    0.06
    Cal
    0.06
     guardians
    0.06
     oranı
    0.06
    Act Density 0.000%

    No Known Activations