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

    Neuronpedia

    INDEX
    Explanations

    rand

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect occurrences of the standard C/C++ “rand” random‐number generator function.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     supervisors
    -0.07
    .mobile
    -0.06
    ayah
    -0.06
     infections
    -0.06
     shrine
    -0.06
    ่าว
    -0.06
     IV
    -0.06
     infection
    -0.06
     criticism
    -0.06
    лаж
    -0.06
    POSITIVE LOGITS
     Rand
    0.11
    rand
    0.10
     rand
    0.09
    Rand
    0.08
    unded
    0.08
     RAND
    0.08
     Randall
    0.08
    '&&
    0.07
     defaultCenter
    0.07
    (rand
    0.07
    Act Density 0.002%

    No Known Activations