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

    Neuronpedia

    INDEX
    Explanations

    punctuation and following clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .)
    0.67
    .
    0.66
    ,
    0.64
    ."
    0.57
    :
    0.57
    .]
    0.54
     (
    0.53
    .”
    0.52
    )
    0.52
     {
    0.51
    POSITIVE LOGITS
     इसमें
    0.59
     journée
    0.55
     jedna
    0.55
     takže
    0.53
    इसमें
    0.53
     exudes
    0.52
    जेक्शन
    0.52
    骅
    0.51
     يمكن
    0.51
     représente
    0.50
    Act Density 0.000%

    No Known Activations