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

    Neuronpedia

    INDEX
    Explanations

    -e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bin
    -0.07
    orde
    -0.07
     bullish
    -0.06
     cured
    -0.06
    yor
    -0.06
    �
    -0.06
     extend
    -0.06
    Haunted
    -0.06
     sets
    -0.06
     cinco
    -0.06
    POSITIVE LOGITS
    @implementation
    0.07
     Teh
    0.07
    ванов
    0.06
    _SPACE
    0.06
    자기
    0.06
     色
    0.06
    万元
    0.06
    monthly
    0.06
    人民
    0.06
     Interview
    0.06
    Act Density 0.025%

    No Known Activations