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

    Neuronpedia

    INDEX
    Explanations

    software versions

    np_max-act · gemini-2.0-flash

    The neuron detects version number strings (e.g. “2.5.10”, “0.5.2”) in changelog entries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .NotNull
    -0.07
    -ret
    -0.06
    instr
    -0.06
    LEncoder
    -0.06
    iotic
    -0.06
    \Factory
    -0.06
    经过
    -0.06
    ünchen
    -0.06
    Ce
    -0.06
    Utils
    -0.06
    POSITIVE LOGITS
    	String
    0.07
     Olomou
    0.07
    Sum
    0.07
     Sum
    0.07
    arranty
    0.07
    �
    0.07
    ])));↵
    0.06
     gripping
    0.06
     armor
    0.06
     bonus
    0.06
    Act Density 0.002%

    No Known Activations