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

    Neuronpedia

    INDEX
    Explanations

    mathematical comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Scheduled
    -0.08
    balls
    -0.07
     lost
    -0.07
    ihan
    -0.07
     ace
    -0.07
     crap
    -0.07
     DEV
    -0.07
    dling
    -0.07
    倒霉
    -0.07
     hell
    -0.07
    POSITIVE LOGITS
    FINITY
    0.07
     Econ
    0.07
    conomy
    0.07
    _OPERATION
    0.07
    workers
    0.07
    增值税
    0.07
    回合
    0.07
    _anchor
    0.07
    砭
    0.07
     Eco
    0.07
    Act Density 0.230%

    No Known Activations