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

    Neuronpedia

    INDEX
    Explanations

    Time and duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     profession
    -0.07
    imension
    -0.07
    _interaction
    -0.07
     Sind
    -0.07
    /usr
    -0.07
    lems
    -0.07
     weighted
    -0.07
    .age
    -0.07
    Democratic
    -0.07
     Qu
    -0.07
    POSITIVE LOGITS
    🏞
    0.07
    氛
    0.07
    캴
    0.07
    谥
    0.07
     числ
    0.07
     kẻ
    0.07
    _APPRO
    0.07
    _MARK
    0.06
     możesz
    0.06
    '];
    0.06
    Act Density 0.007%

    No Known Activations