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

    Neuronpedia

    INDEX
    Explanations

    runner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enabled
    -0.07
    ぇ
    -0.07
     �
    -0.06
     Console
    -0.06
     adultos
    -0.06
     Sustainable
    -0.06
    -folder
    -0.06
    iro
    -0.06
     hung
    -0.06
     aún
    -0.06
    POSITIVE LOGITS
     projections
    0.06
    �
    0.06
    Weak
    0.06
     Total
    0.06
    익
    0.06
    (nn
    0.06
    effective
    0.06
    (short
    0.06
     spare
    0.06
     Triple
    0.06
    Act Density 0.000%

    No Known Activations