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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cancel
    -0.07
    只有
    -0.07
    甲
    -0.07
    Entries
    -0.07
    Alamat
    -0.07
    Interior
    -0.06
    耳
    -0.06
                                ↵
    -0.06
    /music
    -0.06
     pending
    -0.06
    POSITIVE LOGITS
    STYPE
    0.07
    (trace
    0.06
     추가
    0.06
     morph
    0.06
     Moist
    0.06
     하
    0.06
     splice
    0.06
    ré
    0.06
     SER
    0.06
     aime
    0.06
    Act Density 0.259%

    No Known Activations