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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     use
    -0.07
     uses
    -0.07
    Brand
    -0.06
     dés
    -0.06
    Suit
    -0.06
     rych
    -0.06
     Dok
    -0.06
    /am
    -0.06
    -health
    -0.06
     Bolt
    -0.06
    POSITIVE LOGITS
    getStyle
    0.07
    move
    0.06
    $time
    0.06
    (angle
    0.06
    ileaks
    0.06
    (lista
    0.06
    /Product
    0.06
    ;';↵
    0.06
    166
    0.06
     Lista
    0.06
    Act Density 0.002%

    No Known Activations