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

    Neuronpedia

    INDEX
    Explanations

    of the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ü
    -0.07
     forces
    -0.07
     upwards
    -0.07
    scopes
    -0.06
     isol
    -0.06
    $header
    -0.06
    .Users
    -0.06
    _CTRL
    -0.06
     HOUR
    -0.06
     "="
    -0.06
    POSITIVE LOGITS
     інт
    0.07
    /csv
    0.07
    _proba
    0.06
    _BOUNDS
    0.06
    げ
    0.06
    {
↵
↵
    0.06
     Halifax
    0.06
     trước
    0.06
    ..:
    0.06
     Description
    0.06
    Act Density 0.001%

    No Known Activations