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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
    しています
    -0.06
    μό
    -0.06
    ために
    -0.06
    organ
    -0.06
    _capture
    -0.06
     Bog
    -0.06
    example
    -0.06
    _stmt
    -0.06
    ++){↵
    -0.05
    POSITIVE LOGITS
    MASConstraintMaker
    0.07
    (fp
    0.07
    _FRONT
    0.07
     MP
    0.07
    …it
    0.06
    [vertex
    0.06
    uced
    0.06
    styleType
    0.06
     CONCAT
    0.06
    ERVED
    0.06
    Act Density 0.045%

    No Known Activations