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

    Neuronpedia

    INDEX
    Explanations

    code syntax characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sexuality
    -0.08
     LF
    -0.07
    íky
    -0.06
    aser
    -0.06
    โร
    -0.06
    ッチ
    -0.06
     scooter
    -0.06
    LV
    -0.06
     ліс
    -0.06
    ция
    -0.06
    POSITIVE LOGITS
    739
    0.07
    !
    0.07
    Statistic
    0.06
    ="-
    0.06
     Background
    0.06
    ()%
    0.06
    ,"↵
    0.06
     reconsider
    0.06
    .reply
    0.06
    ValuePair
    0.06
    Act Density 0.004%

    No Known Activations