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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kontakte
    -0.07
    �
    -0.06
    εις
    -0.06
    다면
    -0.06
     eskort
    -0.06
    angel
    -0.06
    Tại
    -0.06
    tul
    -0.06
     кла
    -0.06
     highlighted
    -0.06
    POSITIVE LOGITS
    Quaternion
    0.07
    _pt
    0.07
    ffects
    0.07
     Malone
    0.07
    _MR
    0.06
    ♠
    0.06
    	Mat
    0.06
    -name
    0.06
    (boost
    0.06
    =Integer
    0.06
    Act Density 0.000%

    No Known Activations