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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lj
    -0.06
     compan
    -0.06
    virt
    -0.06
     eing
    -0.06
    ového
    -0.06
     coloured
    -0.06
     commuting
    -0.06
    .library
    -0.06
     connexion
    -0.06
    Reaction
    -0.06
    POSITIVE LOGITS
     مطال
    0.07
     produce
    0.06
     recognizing
    0.06
    .vocab
    0.06
    (GPIO
    0.06
     Certainly
    0.06
    �
    0.06
     تص
    0.06
    ognito
    0.06
    リン
    0.06
    Act Density 0.000%

    No Known Activations