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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens—especially CSS/JS numeric values (including floats and numbers with units).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    От
    -0.07
    .:.:.:.
    -0.07
     TString
    -0.06
    Synopsis
    -0.06
     jackets
    -0.06
    Colour
    -0.06
    Bus
    -0.06
    Alabama
    -0.06
    Di
    -0.06
     wallpaper
    -0.06
    POSITIVE LOGITS
     neon
    0.06
     crimes
    0.06
    upply
    0.06
    rif
    0.06
    -led
    0.06
    озв
    0.06
    no
    0.06
    σα
    0.06
     differentiated
    0.06
     taco
    0.06
    Act Density 0.004%

    No Known Activations