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

    Neuronpedia

    INDEX
    Explanations

    specific measurements and units related to scientific data

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

    numerical measurements and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.39
     Hände
    -0.35
     хто
    -0.35
     although
    -0.35
     agujas
    -0.35
     Händen
    -0.34
     متعلقه
    -0.34
     Szy
    -0.33
     Penggunaan
    -0.33
    HIND
    -0.33
    POSITIVE LOGITS
    الحياه
    0.75
    expandindo
    0.56
    EndContext
    0.54
     '\\;'
    0.52
    Jereo
    0.51
    bufio
    0.51
    RectangleBorder
    0.51
    ########.
    0.49
    hecta
    0.49
     OMITBAD
    0.48
    Act Density 0.107%

    No Known Activations