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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash

    This neuron activates on floating‐point number tokens (e.g. decimal scores/weights like “2.876953125,” “0.685546875,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     декоратив
    -0.07
    .Remove
    -0.07
    TabPage
    -0.06
    .spawn
    -0.06
     Icon
    -0.06
     Clo
    -0.06
     Wholesale
    -0.06
    .FileOutputStream
    -0.06
     기다
    -0.06
    amental
    -0.06
    POSITIVE LOGITS
     byt
    0.07
    )*(
    0.07
     nr
    0.06
     Args
    0.06
     ;-
    0.06
     pads
    0.06
     zg
    0.06
     Cairo
    0.06
     µ
    0.06
     harmony
    0.06
    Act Density 0.012%

    No Known Activations