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

    Neuronpedia

    INDEX
    Explanations

    qualifications and exceptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     示例
    -0.07
    ⇐
    -0.07
    😌
    -0.07
    	file
    -0.07
    好消息
    -0.07
     unintended
    -0.07
     JM
    -0.07
    祭祀
    -0.07
    _mod
    -0.07
    建国
    -0.07
    POSITIVE LOGITS
     Absolute
    0.07
    .Quantity
    0.07
    Set
    0.07
    在当地
    0.07
    .histogram
    0.07
    APH
    0.07
    ربع
    0.07
    PEAR
    0.07
    .paginator
    0.07
    (Current
    0.07
    Act Density 0.135%

    No Known Activations