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

    Neuronpedia

    INDEX
    Explanations

    Don't Ask, Don't Tell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esting
    -0.07
    ów
    -0.06
    ObjectName
    -0.06
    UIL
    -0.06
     aboard
    -0.06
     mistake
    -0.06
     ASN
    -0.06
    еро
    -0.06
    -0.06
    getPath
    -0.06
    POSITIVE LOGITS
    ("#{
    0.07
    Glass
    0.07
    mızı
    0.06
    tiles
    0.06
    уч
    0.06
    osci
    0.06
    mesine
    0.06
     Theresa
    0.05
    .BooleanField
    0.05
     Pete
    0.05
    Act Density 0.005%

    No Known Activations