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

    Neuronpedia

    INDEX
    Explanations

    Code, memory objects, bitmaps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ACTIVE
    -0.08
    inactive
    -0.07
    行业的
    -0.07
    ㈯
    -0.07
    <Key
    -0.06
    ימה
    -0.06
    queeze
    -0.06
    Overflow
    -0.06
    废弃物
    -0.06
     intervening
    -0.06
    POSITIVE LOGITS
    .addObserver
    0.07
    漷
    0.07
    ()]↵↵
    0.07
     bloc
    0.07
    意大利
    0.07
    чер
    0.07
    !")↵↵
    0.07
    ulled
    0.07
     //~
    0.07
    	↵
    0.06
    Act Density 0.004%

    No Known Activations