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

    Neuronpedia

    INDEX
    Explanations

    code comments/symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Index
    -0.08
    ubu
    -0.07
     entities
    -0.07
    Wire
    -0.06
     net
    -0.06
    IER
    -0.06
     Mane
    -0.06
     tid
    -0.06
     personalities
    -0.06
    )],↵
    -0.06
    POSITIVE LOGITS
    errorMsg
    0.07
    _PIPE
    0.07
    :s
    0.06
     daycare
    0.06
     stained
    0.06
    .argv
    0.06
     möglich
    0.06
     webdriver
    0.06
     висок
    0.06
    мовір
    0.06
    Act Density 0.022%

    No Known Activations