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

    Neuronpedia

    INDEX
    Explanations

    Code/hash values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >(),
    -0.06
    .term
    -0.06
    >//
    -0.06
    πού
    -0.06
    approved
    -0.06
    專
    -0.06
    /cards
    -0.06
     wound
    -0.06
    slice
    -0.06
    critical
    -0.06
    POSITIVE LOGITS
    uds
    0.07
    tk
    0.07
    _classes
    0.06
     Esta
    0.06
     всё
    0.06
     conspir
    0.06
     durante
    0.06
     pop
    0.06
     ||
↵
    0.06
     příspěv
    0.06
    Act Density 0.008%

    No Known Activations