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

    Neuronpedia

    INDEX
    Explanations

    "When I heard" phrase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     openness
    -0.08
    DoubleClick
    -0.08
    stick
    -0.07
     влаж
    -0.07
     Billy
    -0.07
     league
    -0.07
     vomiting
    -0.07
    .Ct
    -0.07
    闘
    -0.07
     Neville
    -0.07
    POSITIVE LOGITS
    たし
    0.06
     legion
    0.06
     модели
    0.06
     fontSize
    0.06
    <Employee
    0.06
    acades
    0.06
     adulti
    0.06
     rune
    0.06
    lparr
    0.06
     обмеж
    0.06
    Act Density 0.034%

    No Known Activations