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

    Neuronpedia

    INDEX
    Explanations

    finite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    社会
    -0.08
    mployee
    -0.07
     수행
    -0.07
     ':'
    -0.07
    рем
    -0.06
     hated
    -0.06
    	mp
    -0.06
     planting
    -0.06
     withheld
    -0.06
     responseObject
    -0.06
    POSITIVE LOGITS
    /settings
    0.07
     Gover
    0.06
     estilo
    0.06
    [right
    0.06
    _prim
    0.06
     conclusions
    0.06
    ()}</
    0.06
    tube
    0.05
    نه
    0.05
     каче
    0.05
    Act Density 0.004%

    No Known Activations