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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing capability or potential in an informative context

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

    can try achieve add

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.42
     washing
    -0.41
    țul
    -0.40
     Hanson
    -0.39
    chie
    -0.39
     Belong
    -0.39
     Seeking
    -0.39
    Demografía
    -0.39
     сня
    -0.38
    AMBI
    -0.38
    POSITIVE LOGITS
    GEBURTSDATUM
    0.50
    可见
    0.46
    تقاوى
    0.43
     يتيمه
    0.43
    MessageTagHelper
    0.43
    xase
    0.41
    bleau
    0.40
     practicable
    0.40
    codable
    0.40
     հղումներ
    0.39
    Act Density 0.032%

    No Known Activations