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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vez
    -0.07
    glass
    -0.06
     disposed
    -0.06
    Formula
    -0.06
     disclosed
    -0.06
     Sure
    -0.06
    Favorite
    -0.06
    purchase
    -0.06
     nurturing
    -0.06
     Ideal
    -0.06
    POSITIVE LOGITS
    》（
    0.07
    (handle
    0.07
     />';↵
    0.07
    \Blueprint
    0.07
    .HashMap
    0.07
    /target
    0.06
     StringField
    0.06
    [...,
    0.06
     Ген
    0.06
    (NAME
    0.06
    Act Density 0.256%

    No Known Activations