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

    Neuronpedia

    INDEX
    Explanations

    whaling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    errer
    -0.08
     Explor
    -0.08
    ケット
    -0.08
    omeen
    -0.08
     χαρακτηρισ
    -0.07
     ff
    -0.07
     deterioration
    -0.07
     yaran
    -0.07
     needles
    -0.07
    (ele
    -0.07
    POSITIVE LOGITS
    Wikipedia
    0.08
     Wikipedia
    0.08
    ح
    0.08
     Woh
    0.08
     Bayesian
    0.08
     بلا
    0.07
    -efficient
    0.07
     turpis
    0.07
     efficient
    0.07
     inefficient
    0.07
    Act Density 0.001%

    No Known Activations