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

    Neuronpedia

    INDEX
    Explanations

    User stories ("I want...")

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cocoa
    -0.06
    jection
    -0.06
     reviewing
    -0.06
    urd
    -0.06
    crest
    -0.06
     nearly
    -0.06
    695
    -0.06
    Token
    -0.06
    509
    -0.06
    Units
    -0.06
    POSITIVE LOGITS
     Man
    0.07
     Bí
    0.06
     석
    0.06
     sebagai
    0.06
     secured
    0.06
    SKIP
    0.06
     переб
    0.06
    ìm
    0.06
     sling
    0.06
    <Base
    0.06
    Act Density 0.048%

    No Known Activations