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

    Neuronpedia

    INDEX
    Explanations

    Brand names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тощо
    -0.07
    .Maximum
    -0.07
    times
    -0.06
     بخشی
    -0.06
    Form
    -0.06
     bombed
    -0.06
    website
    -0.06
    iterations
    -0.06
    ...'
    -0.06
     Deg
    -0.06
    POSITIVE LOGITS
    vé
    0.08
     Evan
    0.07
    nav
    0.07
    ovo
    0.07
    aven
    0.07
     Alv
    0.07
     aviation
    0.07
    vo
    0.07
     pv
    0.07
    AVIS
    0.07
    Act Density 0.098%

    No Known Activations