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

    Neuronpedia

    INDEX
    Explanations

    ethics/morality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    退税
    -0.07
    本科
    -0.07
    Elf
    -0.07
    soever
    -0.06
    _SER
    -0.06
    谌
    -0.06
    ambil
    -0.06
    urname
    -0.06
    signed
    -0.06
     Movie
    -0.06
    POSITIVE LOGITS
     CST
    0.08
     ozone
    0.07
    バイ
    0.07
     Booster
    0.07
    条例
    0.07
    ZERO
    0.07
     diversity
    0.07
     connections
    0.07
     Wired
    0.07
    .isNotBlank
    0.07
    Act Density 0.012%

    No Known Activations