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

    Neuronpedia

    INDEX
    Explanations

    variation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amounts
    -0.08
    >H
    -0.07
     Además
    -0.07
    ritos
    -0.07
    .As
    -0.07
    ulado
    -0.06
    ожд
    -0.06
     lecture
    -0.06
     tantal
    -0.06
    ARING
    -0.06
    POSITIVE LOGITS
     Chapman
    0.07
     invalidated
    0.06
    /'.$
    0.06
    .Millisecond
    0.06
     imgs
    0.06
     Pizza
    0.06
    _APPRO
    0.06
    保险
    0.06
     EMAIL
    0.06
    くる
    0.06
    Act Density 0.005%

    No Known Activations