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

    Neuronpedia

    INDEX
    Explanations

    intensifiers that emphasize the quality of something, particularly using the word "really"

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

    really followed by positive description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    krist
    -0.49
     mere
    -0.44
     treasure
    -0.43
     Pedersen
    -0.43
     bridges
    -0.43
     technological
    -0.42
     damned
    -0.41
    IndexOutOfBounds
    -0.41
    dams
    -0.41
    catraz
    -0.41
    POSITIVE LOGITS
     NSCoder
    0.55
     محفوظة
    0.46
    CppMethod
    0.45
     ModelExpression
    0.43
    enumii
    0.42
     يتيمه
    0.42
    ValueStyle
    0.42
     betweenstory
    0.42
    enumi
    0.41
    BufferException
    0.40
    Act Density 0.043%

    No Known Activations