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

    Neuronpedia

    INDEX
    Explanations

    preparing students

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     божомолу
    0.48
    㦣
    0.47
    slotBox
    0.47
     vải
    0.47
     Avalanche
    0.47
     ક્ષ
    0.47
     টুল
    0.46
     próximo
    0.46
    ισ
    0.46
     fração
    0.45
    POSITIVE LOGITS
    install
    0.42
     I
    0.42
    gab
    0.42
    har
    0.41
    ("
    0.41
    War
    0.41
     install
    0.40
    Court
    0.40
    ैमर
    0.40
    solve
    0.39
    Act Density 0.001%

    No Known Activations