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

    Neuronpedia

    INDEX
    Explanations

    letters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tranquilidad
    0.38
     vielä
    0.38
     aniversario
    0.38
     baisse
    0.38
     bienvenidas
    0.37
     lupa
    0.37
    ेलकम
    0.37
     cumpleaños
    0.36
     무료
    0.36
    ترة
    0.36
    POSITIVE LOGITS
    ℤ
    0.34
    字母
    0.34
     A
    0.33
    \
    0.33
    PP
    0.32
    Set
    0.31
    alphabet
    0.31
    数学
    0.31
    ABCD
    0.31
    $\
    0.31
    Act Density 0.005%

    No Known Activations