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

    Neuronpedia

    INDEX
    Explanations

    loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loss
    -0.88
    loss
    -0.76
     losses
    -0.74
    Loss
    -0.73
     Loss
    -0.71
     lost
    -0.68
     lose
    -0.66
     LOSS
    -0.66
     loses
    -0.63
    LOSS
    -0.62
    POSITIVE LOGITS
     ProtoMessage
    0.90
    Obrázky
    0.84
    Chham
    0.79
    MessageOf
    0.78
    bootstrapcdn
    0.73
    GEBURTSDATUM
    0.73
    帖最后由
    0.73
     незавершена
    0.72
    enderror
    0.69
    Personensuche
    0.65
    Act Density 0.170%

    No Known Activations