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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron is specialized to pick out numeric literals (numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    )}.
    -0.06
     getSystemService
    -0.06
    IRO
    -0.06
     есте
    -0.06
     Bronze
    -0.06
    }_{
    -0.06
    lications
    -0.06
     diseases
    -0.06
     Governors
    -0.06
    }><
    -0.06
    POSITIVE LOGITS
     bir
    0.07
    64
    0.06
     συμβ
    0.06
     змін
    0.06
     bout
    0.06
    ibrated
    0.06
    .Stderr
    0.06
     temin
    0.06
     �
    0.06
    �ng
    0.06
    Act Density 0.005%

    No Known Activations