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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Divine
    -0.08
    (#)
    -0.07
    بية
    -0.07
    hiro
    -0.06
    Insn
    -0.06
    itial
    -0.06
    赶
    -0.06
    .LoggerFactory
    -0.06
    _flow
    -0.06
    다가
    -0.06
    POSITIVE LOGITS
     пом
    0.07
    fixed
    0.06
    Badge
    0.06
     RuntimeError
    0.06
     battlefield
    0.06
     shorts
    0.06
    UserDefaults
    0.06
    _sibling
    0.06
     Rom
    0.06
    Pag
    0.06
    Act Density 0.025%

    No Known Activations