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

    Neuronpedia

    INDEX
    Explanations

    focus on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    0.91
    otin
    0.81
    ists
    0.78
    ien
    0.77
    ied
    0.74
    ist
    0.73
    ong
    0.72
     &
    0.72
    luk
    0.72
    ä
    0.71
    POSITIVE LOGITS
     equipes
    0.87
     esigen
    0.85
     имен
    0.82
     tentativas
    0.81
     sueños
    0.80
     salário
    0.80
     Neues
    0.79
     dovrà
    0.79
    多様
    0.78
     universidades
    0.78
    Act Density 0.003%

    No Known Activations