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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     numbering
    -0.06
    _aes
    -0.06
     Romero
    -0.06
    Witness
    -0.06
    _include
    -0.06
    Seek
    -0.06
    ']]);↵
    -0.06
    590
    -0.06
     Голов
    -0.06
    _fetch
    -0.06
    POSITIVE LOGITS
     COLL
    0.07
    If
    0.07
     multit
    0.07
     forsk
    0.07
     PG
    0.07
     curt
    0.06
    lightly
    0.06
    武器
    0.06
     prep
    0.06
     wrest
    0.06
    Act Density 0.045%

    No Known Activations