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

    Neuronpedia

    INDEX
    Explanations

    fix

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rhyme
    -0.08
     actress
    -0.07
    眚
    -0.07
    𫢸
    -0.07
    Winner
    -0.07
     Personality
    -0.07
    ihanna
    -0.07
     fighter
    -0.07
    识
    -0.07
    ション
    -0.07
    POSITIVE LOGITS
    手动
    0.07
    outil
    0.07
    改为
    0.07
    _MOBILE
    0.07
    rolling
    0.07
     ")"↵
    0.07
    (label
    0.06
     إن
    0.06
     мне
    0.06
    operator
    0.06
    Act Density 0.021%

    No Known Activations