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 fires on numeric literals—especially floating-point numbers—in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     信
    -0.07
     CCD
    -0.06
    �
    -0.06
     TP
    -0.06
    ीं
    -0.06
    _tcp
    -0.06
    ACA
    -0.06
    ت
    -0.06
     tavsiye
    -0.06
     chữa
    -0.06
    POSITIVE LOGITS
     Virgin
    0.06
     Goodman
    0.06
     goddess
    0.06
     adore
    0.06
     плеч
    0.06
    /validation
    0.06
     μπορεί
    0.06
    asty
    0.06
     Specific
    0.06
    Grace
    0.06
    Act Density 0.039%

    No Known Activations