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

    Neuronpedia

    INDEX
    Explanations

    advocacy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frames
    -0.07
     Jasper
    -0.06
     tanı
    -0.06
    Restart
    -0.06
     laut
    -0.06
    rees
    -0.06
    (false
    -0.06
     Fehler
    -0.06
     fizz
    -0.06
    repositories
    -0.06
    POSITIVE LOGITS
     advocating
    0.09
     advocates
    0.08
    ov
    0.08
     advocacy
    0.08
    FOX
    0.08
    .AUTH
    0.07
    Adv
    0.07
     advocated
    0.07
     Advoc
    0.07
    OV
    0.07
    Act Density 0.005%

    No Known Activations