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

    Neuronpedia

    INDEX
    Explanations

    people's names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	fr
    -0.06
     communicated
    -0.06
    thenReturn
    -0.06
     ques
    -0.06
     Geoff
    -0.06
    mnop
    -0.06
    acted
    -0.06
    fffffff
    -0.06
     Luke
    -0.06
    bsub
    -0.06
    POSITIVE LOGITS
    _png
    0.08
    .Desc
    0.07
    .car
    0.07
     scour
    0.06
     Som
    0.06
    歩いて
    0.06
    قوة
    0.06
    高温
    0.06
     torture
    0.06
    뻗
    0.06
    Act Density 0.021%

    No Known Activations