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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    従
    -0.07
    -fat
    -0.06
     happen
    -0.06
    Walking
    -0.06
     onions
    -0.06
     corridor
    -0.06
     crop
    -0.06
     Hipp
    -0.06
    環
    -0.06
     MSM
    -0.06
    POSITIVE LOGITS
     кня
    0.08
    ateur
    0.08
    (Conv
    0.07
     IsPlainOldData
    0.07
     persön
    0.06
    $config
    0.06
     skvěl
    0.06
     lightning
    0.06
    kır
    0.06
    /testify
    0.06
    Act Density 0.044%

    No Known Activations