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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash

    This neuron fires on quantitative statistical tokens—numbers (especially decimal values), percentages, ratios, and other numeric data in study results.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (add
    -0.07
    (http
    -0.06
    _Dep
    -0.06
    _P
    -0.06
     enraged
    -0.06
     Fast
    -0.06
    .Unit
    -0.06
     Pence
    -0.06
    .orm
    -0.05
    Out
    -0.05
    POSITIVE LOGITS
     жив
    0.07
    险
    0.07
    .wrapper
    0.07
    /testify
    0.07
     تص
    0.07
    후
    0.07
    SCALL
    0.07
    럽
    0.07
    ≠
    0.07
    ileges
    0.06
    Act Density 0.136%

    No Known Activations