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

    Neuronpedia

    INDEX
    Explanations

    hope

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     biting
    -0.08
     snippet
    -0.07
    蔌
    -0.07
    יעה
    -0.07
    🥛
    -0.07
    AUSE
    -0.07
    ː
    -0.06
    (fullfile
    -0.06
    泷
    -0.06
    買った
    -0.06
    POSITIVE LOGITS
     Pay
    0.08
     Maya
    0.07
     caste
    0.06
     SEX
    0.06
    氧化
    0.06
    cas
    0.06
    Play
    0.06
    ,size
    0.06
    .)↵
    0.06
    还将
    0.06
    Act Density 0.015%

    No Known Activations