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

    Neuronpedia

    INDEX
    Explanations

    mand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     part
    -0.07
     expressions
    -0.07
     ż
    -0.07
    žít
    -0.06
    	best
    -0.06
    dür
    -0.06
    -Col
    -0.06
    hn
    -0.06
     veter
    -0.06
    Field
    -0.06
    POSITIVE LOGITS
    ерина
    0.07
    /Images
    0.07
     Gover
    0.07
     Gen
    0.06
    _Per
    0.06
     Erectile
    0.06
    [Any
    0.06
     Kb
    0.06
    (Token
    0.06
     सरक
    0.06
    Act Density 0.002%

    No Known Activations