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

    Neuronpedia

    INDEX
    Explanations

    peer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ानन
    -0.07
    旅游
    -0.06
    Survey
    -0.06
     بانک
    -0.06
    Israel
    -0.06
    /q
    -0.06
     viper
    -0.05
    REDIT
    -0.05
    conditionally
    -0.05
    atches
    -0.05
    POSITIVE LOGITS
    kových
    0.07
    ahas
    0.07
     Vote
    0.07
    بینی
    0.07
    ');?>↵
    0.06
    кості
    0.06
     Floral
    0.06
    ）:
    0.06
    YM
    0.06
    rote
    0.06
    Act Density 0.001%

    No Known Activations