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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     penalty
    -0.07
     Penalty
    -0.06
     permission
    -0.06
    NullException
    -0.06
    degree
    -0.06
     الزر
    -0.06
     Fiscal
    -0.06
     prefers
    -0.06
    struction
    -0.06
    ibu
    -0.06
    POSITIVE LOGITS
    _and
    0.09
    .mouse
    0.08
    And
    0.07
    -and
    0.07
    _AND
    0.07
     THEN
    0.06
    並
    0.06
    よく
    0.06
    ादन
    0.06
    .setRequest
    0.06
    Act Density 0.016%

    No Known Activations