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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on low‐level file I/O and system call identifiers (e.g. read, close, lseek, stat, unistd.h).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    )*
    -0.06
    olarity
    -0.06
     امام
    -0.06
     sple
    -0.06
    })(
    -0.06
    GD
    -0.06
     trusted
    -0.06
     Marsh
    -0.06
     texts
    -0.06
     analsex
    -0.06
    POSITIVE LOGITS
    /stat
    0.07
     Hyper
    0.06
     cesty
    0.06
     medicinal
    0.06
    ‌ها
    0.06
     Tôi
    0.06
     đi
    0.06
    SUR
    0.06
    シー
    0.06
    \Post
    0.06
    Act Density 0.010%

    No Known Activations