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

    Neuronpedia

    INDEX
    Explanations

    answer choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mesma
    0.38
     bahan
    0.35
    
    0.35
    hattim
    0.34
    োপ
    0.34
     mesmas
    0.34
     tarefa
    0.33
    لمانيا
    0.33
    ্যান
    0.32
     pewno
    0.32
    POSITIVE LOGITS
     Property
    0.36
    비
    0.35
     Two
    0.33
     Crack
    0.32
     &
    0.32
    Property
    0.32
     "
    0.31
     deux
    0.31
     P
    0.31
     for
    0.30
    Act Density 0.010%

    No Known Activations