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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .once
    -0.08
    _Pre
    -0.07
    ALLED
    -0.06
    /exp
    -0.06
     []:↵
    -0.06
    .tv
    -0.06
     англ
    -0.06
    /al
    -0.06
    %'↵
    -0.06
     editable
    -0.06
    POSITIVE LOGITS
     consum
    0.08
     TNT
    0.07
    авис
    0.06
     Consum
    0.06
     Locker
    0.06
    ‎
    0.06
     awesome
    0.06
     التش
    0.06
    .ShowDialog
    0.06
     catching
    0.06
    Act Density 0.163%

    No Known Activations