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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wrench
    -0.07
    _segments
    -0.06
     inspection
    -0.06
    .SUB
    -0.06
     collided
    -0.06
    _N
    -0.06
    	data
    -0.06
    ुभव
    -0.06
    处理
    -0.06
    .audio
    -0.06
    POSITIVE LOGITS
     adoles
    0.07
    کیل
    0.07
    .uf
    0.07
    (inputs
    0.06
     baise
    0.06
    ((-
    0.06
     깨
    0.06
     privileged
    0.06
     dikkat
    0.06
     chiff
    0.06
    Act Density 0.119%

    No Known Activations