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

    Neuronpedia

    INDEX
    Explanations

    code snippets involving conditional statements and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens after "if" or "whether"

    np_acts-logits-general · gemini-2.0-flash

    whether if id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.76
     betweenstory
    -0.70
    GEBURTSDATUM
    -0.69
    oredCriteria
    -0.65
     Seeder
    -0.63
    AndEndTag
    -0.60
    bootstrapcdn
    -0.59
     gynhyrchwyd
    -0.58
    TagMode
    -0.58
     ComVisible
    -0.58
    POSITIVE LOGITS
     whose
    0.40
    A
    0.39
     whether
    0.39
    whether
    0.39
    ceğini
    0.39
    Whether
    0.37
     voici
    0.37
     geçir
    0.36
     WHETHER
    0.36
     Puedes
    0.35
    Act Density 0.183%

    No Known Activations