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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens (especially decimal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     getStatus
    -0.07
    ;a
    -0.07
     NSLayoutConstraint
    -0.07
     Mild
    -0.07
    )];
↵
    -0.07
    GLenum
    -0.07
    iptables
    -0.06
    [maxn
    -0.06
     semaphore
    -0.06
     separator
    -0.06
    POSITIVE LOGITS
     curs
    0.07
    uably
    0.06
     goede
    0.06
     embassy
    0.06
    .DisplayStyle
    0.06
     arrival
    0.06
    0.06
    APSHOT
    0.06
    ensively
    0.06
    adresse
    0.06
    Act Density 0.011%

    No Known Activations