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 responds to numeric tokens (especially floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     permitting
    -0.07
     THINK
    -0.06
     Providence
    -0.06
     Kabul
    -0.06
    شمالی
    -0.06
     chest
    -0.06
     Mitarbeiter
    -0.06
    -0.06
     traction
    -0.05
     parler
    -0.05
    POSITIVE LOGITS
     wipe
    0.07
     Lik
    0.07
     Down
    0.06
    istické
    0.06
    "crypto
    0.06
    .Management
    0.06
     ====
    0.06
     +↵
    0.06
     hikes
    0.06
     číslo
    0.06
    Act Density 0.041%

    No Known Activations