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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron strongly activates on low‐level hardware I/O operations (e.g., in_be32, out_be32, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     videos
    -0.07
     visions
    -0.07
     곧
    -0.07
    (lp
    -0.07
     moet
    -0.06
     hombre
    -0.06
     molecular
    -0.06
    ону
    -0.06
    орі
    -0.06
    sts
    -0.06
    POSITIVE LOGITS
     Yankees
    0.07
     cgi
    0.06
    /../
    0.06
    -remove
    0.06
    θεια
    0.05
    면
    0.05
    	style
    0.05
    smooth
    0.05
     IV
    0.05
     sní
    0.05
    Act Density 0.004%

    No Known Activations