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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hour
    -0.06
    Curve
    -0.06
    ,[
    -0.06
    ，《
    -0.06
    -do
    -0.06
     feats
    -0.06
    (["
    -0.06
    ();"
    -0.06
    نجليزية
    -0.06
     erfolgreich
    -0.06
    POSITIVE LOGITS
     reinforcements
    0.07
    ριν
    0.06
     tempor
    0.06
     preserve
    0.06
    vere
    0.06
     eru
    0.06
    ầy
    0.06
    UY
    0.06
    iples
    0.06
     substr
    0.06
    Act Density 0.002%

    No Known Activations