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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     impuls
    -0.06
    銷
    -0.06
     однако
    -0.06
    ็บไซต
    -0.06
    -authored
    -0.06
     như
    -0.06
     tty
    -0.06
    ."),
    -0.06
    (inertia
    -0.06
     fading
    -0.06
    POSITIVE LOGITS
     التع
    0.07
     새
    0.07
    ือข
    0.07
     bigotry
    0.07
     synthetic
    0.07
    getObject
    0.07
    oen
    0.06
    Nuitka
    0.06
    тов
    0.06
     Viking
    0.06
    Act Density 0.003%

    No Known Activations