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

    Neuronpedia

    INDEX
    Explanations

    probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blessés
    -0.66
     scolaires
    -0.65
     stället
    -0.64
     prisonniers
    -0.63
     démocr
    -0.63
     singoli
    -0.63
     pintadas
    -0.59
     récents
    -0.59
     armées
    -0.58
     aisladas
    -0.58
    POSITIVE LOGITS
    Clik
    0.55
     mean
    0.53
    ArgsConstructor
    0.51
     متعلقه
    0.51
     travel
    0.49
    せば
    0.48
     will
    0.48
     UIImage
    0.48
    θν
    0.47
     can
    0.47
    Act Density 0.001%

    No Known Activations