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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect floating-point numeric constants (i.e. numbers containing a decimal point) in code or comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     refrain
    -0.08
     Typography
    -0.07
     death
    -0.06
    Modification
    -0.06
     vamp
    -0.06
    ovice
    -0.06
     asm
    -0.06
    iy
    -0.06
     Moss
    -0.06
     mehr
    -0.06
    POSITIVE LOGITS
    κλη
    0.07
    |;↵
    0.07
    .cli
    0.07
    쳤다
    0.07
    >):
    0.07
    "",↵
    0.07
    lx
    0.06
     "";↵↵
    0.06
                 ↵
    0.06
    "]=$
    0.06
    Act Density 0.001%

    No Known Activations