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

    Neuronpedia

    INDEX
    Explanations

    furnace/blast

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     désir
    -0.08
    Mixed
    -0.07
    /angular
    -0.07
    .Focus
    -0.07
     FileInputStream
    -0.07
    issing
    -0.07
    וי
    -0.07
    手指
    -0.07
    Apr
    -0.07
    ï
    -0.07
    POSITIVE LOGITS
     loại
    0.06
    剧中
    0.06
    onomía
    0.06
    eração
    0.06
    格
    0.06
    药师
    0.06
    para
    0.06
    imentary
    0.06
    kj
    0.06
    حلة
    0.06
    Act Density 0.005%

    No Known Activations