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

    Neuronpedia

    INDEX
    Explanations

    not seeing something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    主张
    -0.07
    importe
    -0.07
    .ndim
    -0.07
    蓑
    -0.07
     guise
    -0.07
    ordion
    -0.07
     Curse
    -0.07
    annies
    -0.06
    借口
    -0.06
    trand
    -0.06
    POSITIVE LOGITS
    随即
    0.07
    首轮
    0.07
     WAL
    0.07
    ᄑ
    0.07
    ()"
    0.07
     Dak
    0.07
    *p
    0.07
     déjà
    0.07
    很满意
    0.07
    	fi
    0.06
    Act Density 0.002%

    No Known Activations