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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fantasy
    -0.07
    新品
    -0.07
    Adjacent
    -0.07
    ⁻
    -0.07
     candid
    -0.07
    [_
    -0.07
     đảm
    -0.07
    _sub
    -0.07
     suspicious
    -0.07
    ◔
    -0.07
    POSITIVE LOGITS
    ISyntaxException
    0.07
     vez
    0.07
    .Hour
    0.07
    Ӣ
    0.06
    مار
    0.06
    𬘘
    0.06
    汧
    0.06
    SpinBox
    0.06
     Mississippi
    0.06
     OR
    0.06
    Act Density 0.003%

    No Known Activations