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

    Neuronpedia

    INDEX
    Explanations

    Words starting with "Cav"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .startswith
    -0.06
    bedo
    -0.06
     Dahl
    -0.06
    เตร
    -0.06
    ضم
    -0.06
     Bentley
    -0.06
    Optimizer
    -0.06
     "{}
    -0.06
     içeri
    -0.05
     Romeo
    -0.05
    POSITIVE LOGITS
    adia
    0.08
     assured
    0.07
     Religion
    0.07
     člen
    0.07
    Dummy
    0.06
     folly
    0.06
     ningún
    0.06
     Guide
    0.06
     hypotheses
    0.06
    .Pay
    0.06
    Act Density 0.005%

    No Known Activations