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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -unstyled
    -0.07
    名列
    -0.07
     thrilled
    -0.07
    полит
    -0.07
     Cardiff
    -0.07
    ΰ
    -0.07
    一楼
    -0.07
    耱
    -0.07
     Gòn
    -0.07
    -intensive
    -0.07
    POSITIVE LOGITS
    Unity
    0.07
    eing
    0.07
    表白
    0.07
    ATCH
    0.07
    UBE
    0.07
    经纬
    0.07
    ющая
    0.06
    Directories
    0.06
     pharmacies
    0.06
    dataset
    0.06
    Act Density 0.000%

    No Known Activations