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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Usually
    -0.07
     MU
    -0.06
     Performs
    -0.06
    PTY
    -0.06
     Laden
    -0.06
    iss
    -0.06
    893
    -0.06
     absorbs
    -0.06
     Usually
    -0.06
    cura
    -0.06
    POSITIVE LOGITS
    ณะ
    0.06
    .ToDouble
    0.06
     γεν
    0.06
    .TextEdit
    0.06
    .Query
    0.06
     stranger
    0.06
    gende
    0.06
    印
    0.06
     الرياض
    0.06
    opause
    0.06
    Act Density 0.136%

    No Known Activations