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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HERE
    -1.14
    HERE
    -0.85
    ./
    -0.84
    SharedDtor
    -0.71
    medriver
    -0.64
     المعيارى
    -0.62
    hips
    -0.62
    oa̍t
    -0.60
    rungsseite
    -0.59
    Morfologia
    -0.59
    POSITIVE LOGITS
     uſe
    0.63
     Monfieur
    0.58
     juſt
    0.57
     ſtate
    0.56
     ſay
    0.55
     paſſ
    0.53
     bershka
    0.52
     poffe
    0.52
     noastre
    0.52
     tranſ
    0.52
    Act Density 0.299%

    No Known Activations