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

    Neuronpedia

    INDEX
    Explanations

    VARCHAR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    投入
    -0.08
    xffff
    -0.08
     energy
    -0.07
     blazing
    -0.07
    _lifetime
    -0.07
     suất
    -0.07
    elf
    -0.06
     ############################################################################
    -0.06
     layoffs
    -0.06
    下降
    -0.06
    POSITIVE LOGITS
     VARCHAR
    0.08
     CONT
    0.07
    缓
    0.07
    _UNUSED
    0.07
     Radius
    0.07
     mamm
    0.07
    𝓭
    0.07
     Concrete
    0.06
    .Com
    0.06
     pillar
    0.06
    Act Density 0.003%

    No Known Activations