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

    Neuronpedia

    INDEX
    Explanations

    Four sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reactive
    -0.09
    ctype
    -0.09
     افز
    -0.08
    Gs
    -0.08
    ुड
    -0.08
    weath
    -0.08
    izziness
    -0.08
    emetery
    -0.07
    كة
    -0.07
    Fig
    -0.07
    POSITIVE LOGITS
     роли
    0.10
     yksi
    0.08
     ausdr
    0.08
    之一
    0.08
    .flash
    0.08
     одном
    0.08
     expresses
    0.08
    一句
    0.08
    &nbsp
    0.08
     தெரிவித்த
    0.08
    Act Density 0.009%

    No Known Activations