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 fires on floating-point numeric literals (decimal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    리를
    -0.08
     fronts
    -0.08
     cabins
    -0.07
     Ruf
    -0.07
    Fuse
    -0.07
    Wake
    -0.07
     Circle
    -0.07
    ier
    -0.07
     برخورد
    -0.06
     Fuse
    -0.06
    POSITIVE LOGITS
     jade
    0.06
    Holder
    0.06
    getDefault
    0.06
    yclic
    0.06
     �
    0.06
    шая
    0.06
    bufio
    0.06
    \_
    0.06
     الاتحاد
    0.06
     »↵
    0.05
    Act Density 0.043%

    No Known Activations