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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols related to probabilities and statistics

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

    Mathematical or scientific expressions

    np_acts-logits-general · gemini-2.0-flash

    formulas with brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <=",
    -0.53
    sidemargin
    -0.53
     CreateTagHelper
    -0.52
    ✭✭
    -0.51
    sizeCache
    -0.51
     صوتيه
    -0.50
    arte
    -0.47
    fjspx
    -0.46
    Statics
    -0.46
    ="@+
    -0.45
    POSITIVE LOGITS
    достатки
    0.63
    omiast
    0.62
    üstung
    0.61
     denominator
    0.57
     partij
    0.54
     esquecer
    0.54
     تانيه
    0.51
    "](
    0.50
    subtract
    0.50
    MethodManager
    0.50
    Act Density 0.623%

    No Known Activations