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

    Neuronpedia

    INDEX
    Explanations

    stem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kil
    -0.07
     giants
    -0.07
    ﷼
    -0.07
    小姐
    -0.07
    visions
    -0.07
    蒱
    -0.06
     macros
    -0.06
    -mouth
    -0.06
    maint
    -0.06
    aaaa
    -0.06
    POSITIVE LOGITS
    感到
    0.07
    stå
    0.07
    _LAYER
    0.07
    重要意义
    0.07
    ступил
    0.06
    _topology
    0.06
    -tm
    0.06
    طار
    0.06
    й
    0.06
    .getRandom
    0.06
    Act Density 0.008%

    No Known Activations