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

    Neuronpedia

    INDEX
    Explanations

    identifiers and numerical data related to technical specifications or attributes

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

    numbers and mixed characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perfección
    -0.32
    ungguh
    -0.32
     cárcel
    -0.31
     sekä
    -0.30
     universidad
    -0.29
     begge
    -0.28
    cheinend
    -0.28
     bangunan
    -0.28
     gjerne
    -0.28
    麼
    -0.28
    POSITIVE LOGITS
    Diweddarwch
    0.98
     Italijanski
    0.88
    ChildScrollView
    0.82
     nakalista
    0.82
     OFDb
    0.81
     zwiſchen
    0.81
     Administrativna
    0.80
    <unused47>
    0.79
    extAlignment
    0.78
    [@BOS@]
    0.78
    Act Density 0.021%

    No Known Activations