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

    Neuronpedia

    INDEX
    Explanations

    deviation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [of
    -0.07
     favoured
    -0.06
     bribery
    -0.06
     prized
    -0.06
    �
    -0.06
    (uri
    -0.06
    Ent
    -0.06
     соль
    -0.06
     lunches
    -0.06
     bezier
    -0.06
    POSITIVE LOGITS
     drawbacks
    0.06
     Investig
    0.06
    DEV
    0.06
    -four
    0.06
    tridges
    0.06
    สน
    0.06
     stopping
    0.06
    jay
    0.06
     drž
    0.06
    AGING
    0.06
    Act Density 0.006%

    No Known Activations