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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    êu
    -0.08
    悪い
    -0.07
    促
    -0.07
     detecting
    -0.07
    (Route
    -0.07
     cause
    -0.07
    _pieces
    -0.07
     perf
    -0.07
    ечение
    -0.07
     médico
    -0.07
    POSITIVE LOGITS
    僦
    0.07
    瞻
    0.07
    HASH
    0.06
     paren
    0.06
    ⊂
    0.06
    僳
    0.06
     uniqueness
    0.06
    _SECONDS
    0.06
     appended
    0.06
     noon
    0.06
    Act Density 0.146%

    No Known Activations