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
    Successfully
    -0.08
     समाचार
    -0.08
     Amazing
    -0.08
     photography
    -0.08
     feminism
    -0.07
     portada
    -0.07
     Miriam
    -0.07
    News
    -0.07
    _TOOL
    -0.07
     MON
    -0.07
    POSITIVE LOGITS
     losses
    0.14
     penalties
    0.12
    耗
    0.12
     perdas
    0.12
     pérdidas
    0.11
     pertes
    0.11
     impurities
    0.11
     incurred
    0.11
    损
    0.11
    _losses
    0.10
    Act Density 0.006%

    No Known Activations