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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash

    The neuron activates on programming control‐flow keywords (like “if,” “else,” “switch,” “for,” “while”) indicating a control structure statement.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (sigma
    -0.07
    _perf
    -0.07
    Γ
    -0.07
     maks
    -0.06
     frække
    -0.06
    DMETHOD
    -0.06
    	State
    -0.06
    production
    -0.06
    ото
    -0.06
     htonl
    -0.06
    POSITIVE LOGITS
    +.
    0.06
     Appears
    0.06
    …………
    0.06
    ху
    0.06
    _",
    0.06
    ocup
    0.06
    。“
    0.06
    MITTED
    0.06
    hind
    0.06
     Hidden
    0.06
    Act Density 0.014%

    No Known Activations