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

    Neuronpedia

    INDEX
    Explanations

    Assertions, recommendations, desires

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pred
    -0.08
    /><
    -0.08
    ndata
    -0.07
    トラ
    -0.07
     Smash
    -0.07
    нет
    -0.07
    -water
    -0.07
    ග
    -0.07
    ⚑
    -0.06
    .colorbar
    -0.06
    POSITIVE LOGITS
    独一无二
    0.07
     hosp
    0.07
     VARCHAR
    0.07
     hug
    0.07
    Because
    0.06
    CLOCKS
    0.06
    奖学金
    0.06
     nấu
    0.06
    oly
    0.06
     summon
    0.06
    Act Density 0.110%

    No Known Activations