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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oj
    -0.06
    Hist
    -0.06
     legalization
    -0.06
     tents
    -0.06
    asıyla
    -0.06
    orget
    -0.06
     Saf
    -0.06
    �
    -0.06
     historian
    -0.06
     Πα
    -0.06
    POSITIVE LOGITS
     ench
    0.07
    onga
    0.06
    :numel
    0.06
    zzle
    0.06
    ジオ
    0.06
     shame
    0.06
     blank
    0.06
    	parameters
    0.06
    .scale
    0.06
     requester
    0.06
    Act Density 0.046%

    No Known Activations