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

    Neuronpedia

    INDEX
    Explanations

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reels
    -0.07
    .REG
    -0.06
     conversion
    -0.06
    _registration
    -0.06
     progression
    -0.06
    肌
    -0.06
    thing
    -0.06
    아요
    -0.06
     GRE
    -0.06
     مرات
    -0.06
    POSITIVE LOGITS
    umd
    0.07
     pours
    0.07
     δε
    0.06
    emat
    0.06
    }")]↵
    0.06
    �
    0.06
    (md
    0.06
    dued
    0.06
    Found
    0.06
     cd
    0.06
    Act Density 0.014%

    No Known Activations