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

    Neuronpedia

    INDEX
    Explanations

    Data comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sd
    -0.07
    ’nda
    -0.06
    opped
    -0.06
    !='
    -0.06
     expelled
    -0.06
    Employees
    -0.06
    Cou
    -0.06
    _right
    -0.06
    àng
    -0.06
    (Socket
    -0.06
    POSITIVE LOGITS
     Scripts
    0.07
     DISP
    0.06
     Jana
    0.06
    KeyValue
    0.06
     гал
    0.06
    ################################################
    0.06
    .storage
    0.06
    [char
    0.06
    .Abs
    0.06
    previous
    0.06
    Act Density 0.000%

    No Known Activations