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

    Neuronpedia

    INDEX
    Explanations

    655

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pain
    -0.08
    _NB
    -0.08
    asia
    -0.07
    皮
    -0.07
    _head
    -0.07
    aped
    -0.07
    ACION
    -0.07
    quan
    -0.07
    	bt
    -0.07
    ूज
    -0.07
    POSITIVE LOGITS
     Slo
    0.07
    409
    0.07
    Lex
    0.06
     Eth
    0.06
     Spect
    0.06
     ALLOW
    0.06
     �
    0.06
    204
    0.06
     GRAPH
    0.06
     Missing
    0.06
    Act Density 0.020%

    No Known Activations