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

    Neuronpedia

    INDEX
    Explanations

    <pre

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cannon
    -0.08
     phenomena
    -0.08
     dengan
    -0.07
     pumpkin
    -0.07
     %(
    -0.07
     statues
    -0.07
    ファ
    -0.07
    weeney
    -0.06
    :)↵
    -0.06
    annon
    -0.06
    POSITIVE LOGITS
    pieczeńst
    0.07
    .eulerAngles
    0.07
     Ogre
    0.07
    }".
    0.07
    뤽
    0.07
    ;charset
    0.07
    lararası
    0.07
     reassuring
    0.07
     Galactic
    0.07
    طن
    0.07
    Act Density 0.021%

    No Known Activations