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

    Neuronpedia

    INDEX
    Explanations

    prefix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ol
    -0.08
     Gam
    -0.08
     Alan
    -0.07
     Loren
    -0.07
    hard
    -0.07
     Holt
    -0.07
    oyal
    -0.07
    Alan
    -0.07
    _goods
    -0.07
     볼
    -0.07
    POSITIVE LOGITS
     Prefix
    0.14
     prefix
    0.13
    Prefix
    0.13
    (prefix
    0.11
    _PREFIX
    0.11
     prefixes
    0.11
    prefix
    0.11
    _prefix
    0.10
     prefixed
    0.09
    .prefix
    0.08
    Act Density 0.007%

    No Known Activations