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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clamation
    -0.08
     forward
    -0.07
     Forward
    -0.07
    binations
    -0.07
    completion
    -0.07
    expression
    -0.07
     校
    -0.07
     sık
    -0.06
     Фор
    -0.06
    öne
    -0.06
    POSITIVE LOGITS
     subtle
    0.08
     calming
    0.08
    .Ui
    0.08
     rédu
    0.07
     pagbaba
    0.07
     finesse
    0.07
     Inicio
    0.07
     tranquil
    0.07
     మంచ
    0.07
    Inicio
    0.07
    Act Density 0.122%

    No Known Activations