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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron is detecting numeric literals (especially floating‐point numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ени
    -0.07
    book
    -0.07
    Ba
    -0.06
     norms
    -0.06
    wrapper
    -0.06
     highlighting
    -0.06
     частина
    -0.06
     ElementType
    -0.06
    ------+------+
    -0.06
     communion
    -0.06
    POSITIVE LOGITS
     bullish
    0.07
                
    0.06
    .AddTransient
    0.06
    ::{↵
    0.06
     LocalDateTime
    0.06
        
    0.06
    μμε
    0.06
    :{
↵
    0.06
    ・・
    0.06
    .FILES
    0.06
    Act Density 0.008%

    No Known Activations