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

    Neuronpedia

    INDEX
    Explanations

    user confirmation/selection interfaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Px
    -0.08
    ीर
    -0.07
     deadlock
    -0.07
    eger
    -0.07
     accessor
    -0.06
    agus
    -0.06
    ipv
    -0.06
    Floor
    -0.06
    unix
    -0.06
    ạng
    -0.06
    POSITIVE LOGITS
    _countries
    0.06
    -rule
    0.06
     acronym
    0.06
     Masks
    0.06
    Cards
    0.06
    layıcı
    0.06
    รร
    0.06
     cata
    0.06
    最初
    0.06
     публі
    0.06
    Act Density 0.060%

    No Known Activations