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

    Neuronpedia

    INDEX
    Explanations

    amplifier classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ULT
    -0.07
    加
    -0.07
     Campo
    -0.06
    kop
    -0.06
    chor
    -0.06
     Robbins
    -0.06
    勢
    -0.06
    уки
    -0.06
     Bolt
    -0.06
    hou
    -0.06
    POSITIVE LOGITS
     student
    0.08
    	file
    0.07
     자신의
    0.07
    cciones
    0.07
    _XML
    0.07
    .send
    0.07
    _IMG
    0.06
     pupil
    0.06
    	payload
    0.06
    	img
    0.06
    Act Density 0.000%

    No Known Activations