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

    Neuronpedia

    INDEX
    Explanations

    Repeating numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nodes
    -0.07
     Bedford
    -0.07
    fft
    -0.06
    irq
    -0.06
    ergarten
    -0.06
    _ghost
    -0.06
     wee
    -0.06
     Superv
    -0.06
    左手
    -0.06
     ut
    -0.06
    POSITIVE LOGITS
     molds
    0.07
     appended
    0.07
    Certainly
    0.07
    >(),↵
    0.06
    >User
    0.06
     ambiguity
    0.06
    misión
    0.06
    "])
↵
    0.06
    >('
    0.06
     warranted
    0.06
    Act Density 0.003%

    No Known Activations