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

    Neuronpedia

    INDEX
    Explanations

    http/https

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ileen
    -0.07
     compact
    -0.07
    Kim
    -0.07
     cư
    -0.07
    材
    -0.07
    精准扶贫
    -0.07
     Bingo
    -0.06
     diet
    -0.06
     Dave
    -0.06
    Pas
    -0.06
    POSITIVE LOGITS
    𝑤
    0.07
    getMessage
    0.07
     abilities
    0.07
    astreet
    0.07
    lıkl
    0.07
    swift
    0.07
     initWith
    0.07
    	damage
    0.07
    螱
    0.07
    अ
    0.06
    Act Density 0.001%

    No Known Activations