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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dangerously
    -0.08
     nuclei
    -0.07
    类型的
    -0.07
    ニュー
    -0.07
     Å
    -0.07
     wanna
    -0.07
     выраж
    -0.07
     allocate
    -0.07
    monary
    -0.07
    _nav
    -0.07
    POSITIVE LOGITS
    Leaks
    0.07
    ne
    0.07
    แดด
    0.07
    вшис
    0.07
    重塑
    0.07
    משקל
    0.07
    .Raw
    0.07
    detalle
    0.07
    fait
    0.07
    gamma
    0.07
    Act Density 0.061%

    No Known Activations