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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    떠
    -0.08
     evangelical
    -0.07
    Stan
    -0.07
     dy
    -0.07
     düzenle
    -0.07
    .NEW
    -0.07
     Senator
    -0.06
     Hans
    -0.06
     pushed
    -0.06
     stained
    -0.06
    POSITIVE LOGITS
     Rating
    0.07
    低廉
    0.07
     retrofit
    0.07
     đình
    0.07
    作弊
    0.07
    .UInt
    0.07
     Lifestyle
    0.06
     Timer
    0.06
    ::{
    0.06
    [edge
    0.06
    Act Density 0.054%

    No Known Activations