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

    Neuronpedia

    INDEX
    Explanations

    ex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _btn
    -0.07
    grese
    -0.07
    蹶
    -0.07
    _cls
    -0.07
    plement
    -0.07
    	left
    -0.07
    lox
    -0.07
    .Get
    -0.07
    加之
    -0.06
    iş
    -0.06
    POSITIVE LOGITS
    _intent
    0.07
     Archae
    0.07
     הי
    0.07
     да
    0.07
    Se
    0.07
     Shore
    0.07
    ﮨ
    0.06
     requisite
    0.06
    𝔻
    0.06
    har
    0.06
    Act Density 0.002%

    No Known Activations