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

    Neuronpedia

    INDEX
    Explanations

    common prepositions or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oll
    0.52
    "));
    0.50
    rit
    0.48
     understand
    0.48
    s
    0.47
     index
    0.47
    public
    0.47
    d
    0.47
    ell
    0.46
    0
    0.46
    POSITIVE LOGITS
     sagging
    0.52
     корпуса
    0.52
    মনসিংহ
    0.51
     neoplastic
    0.51
    ጢ
    0.50
     Mavic
    0.50
    到来
    0.49
     quartic
    0.49
     sempat
    0.48
     пересе
    0.48
    Act Density 0.000%

    No Known Activations