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

    Neuronpedia

    INDEX
    Explanations

    addition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     communicates
    -0.07
     showed
    -0.07
    _sorted
    -0.07
    屏
    -0.06
     önemli
    -0.06
     Berkeley
    -0.06
    Uuid
    -0.06
    .read
    -0.06
     communicate
    -0.06
     brokers
    -0.06
    POSITIVE LOGITS
    illi
    0.08
     additions
    0.08
    addon
    0.08
    ών
    0.07
    シ
    0.07
    entr
    0.07
    finally
    0.07
    ीश
    0.07
     موسی
    0.07
    ixon
    0.07
    Act Density 0.006%

    No Known Activations