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

    Neuronpedia

    INDEX
    Explanations

    conversations and correspondence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Duplicate
    -0.07
    頃
    -0.07
     ordinary
    -0.06
    Vote
    -0.06
     вч
    -0.06
    xBC
    -0.06
    #{@
    -0.06
    -this
    -0.06
    _pa
    -0.06
    .deg
    -0.06
    POSITIVE LOGITS
    ati
    0.08
     danger
    0.07
     Bes
    0.06
    (path
    0.06
    ському
    0.06
    ibus
    0.06
     واقعی
    0.06
     Philips
    0.06
    ,email
    0.06
    ossil
    0.06
    Act Density 0.009%

    No Known Activations