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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ertz
    -0.07
     דיגיטלי
    -0.06
     newArray
    -0.06
    🥩
    -0.06
    鸾
    -0.06
    🐀
    -0.06
    pull
    -0.06
    ilst
    -0.06
    utz
    -0.06
    (errors
    -0.06
    POSITIVE LOGITS
    =self
    0.07
     proclamation
    0.07
    /thumb
    0.07
    Cro
    0.07
    =True
    0.06
    ={$
    0.06
    Replacing
    0.06
     Vaults
    0.06
    صدي
    0.06
    妯
    0.06
    Act Density 0.008%

    No Known Activations