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

    Neuronpedia

    INDEX
    Explanations

    PID

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    executor
    -0.08
     health
    -0.07
    椁
    -0.07
    ཆ
    -0.07
    WWW
    -0.07
    MDB
    -0.07
    江东
    -0.07
     Kub
    -0.07
    โฆ
    -0.07
    ▬
    -0.07
    POSITIVE LOGITS
    前置
    0.07
    _TEMP
    0.07
    💭
    0.07
    ackle
    0.07
    𝚊
    0.07
    abilidade
    0.07
    $array
    0.06
     emanc
    0.06
    adr
    0.06
     averages
    0.06
    Act Density 0.010%

    No Known Activations