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

    Neuronpedia

    INDEX
    Explanations

    command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jos
    -0.07
    Chat
    -0.07
    狀
    -0.07
    דרום
    -0.07
     Trọng
    -0.07
    דמי
    -0.07
     '+'
    -0.07
    AsStream
    -0.07
    osal
    -0.07
    么
    -0.06
    POSITIVE LOGITS
    ILITIES
    0.07
    starttime
    0.07
    _EXTENSIONS
    0.07
    ////////////////////////////////////////////////////
    0.07
    (changes
    0.07
    遍及
    0.07
    soles
    0.07
    ∪
    0.06
    PCR
    0.06
     auditing
    0.06
    Act Density 0.018%

    No Known Activations