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

    Neuronpedia

    INDEX
    Explanations

    please

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    September
    -0.06
    essment
    -0.06
    assed
    -0.06
     platinum
    -0.06
    .collection
    -0.06
     Breitbart
    -0.06
     flushing
    -0.06
    awy
    -0.06
     Sharia
    -0.06
     çocuk
    -0.06
    POSITIVE LOGITS
    _RULE
    0.07
    ++↵↵
    0.06
     sne
    0.06
    _ctrl
    0.06
    })
↵
↵
    0.06
     tra
    0.06
    _P
    0.06
     Requires
    0.06
    mination
    0.06
    mathrm
    0.06
    Act Density 0.015%

    No Known Activations