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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cells
    -0.06
    euillez
    -0.06
     influential
    -0.06
     CRA
    -0.06
     输出
    -0.06
     typography
    -0.06
     boarded
    -0.06
    hibition
    -0.06
     Nevada
    -0.06
    (defvar
    -0.06
    POSITIVE LOGITS
    lanmış
    0.07
    (beta
    0.07
    ук
    0.06
    akat
    0.06
    _generated
    0.06
    ild
    0.06
    igin
    0.06
     toward
    0.06
    ốt
    0.06
    art
    0.06
    Act Density 0.000%

    No Known Activations