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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations or constructs in equations

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

    Mathematical or scientific notation

    np_acts-logits-general · gemini-2.0-flash

    math symbols and scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    иск
    -0.51
     balance
    -0.50
    achi
    -0.48
    eting
    -0.48
     التح
    -0.47
     Mar
    -0.47
     Balk
    -0.47
     ek
    -0.47
     hard
    -0.47
    insp
    -0.47
    POSITIVE LOGITS
    mergeFrom
    0.73
    AndEndTag
    0.73
     termica
    0.69
    IntoConstraints
    0.69
    TypedDataSet
    0.69
    Brainz
    0.68
     wiederum
    0.68
     MainAxisSize
    0.65
     coppia
    0.64
    ImageContext
    0.63
    Act Density 0.496%

    No Known Activations