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

    Neuronpedia

    INDEX
    Explanations

    code execution and output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ле
    1.27
    ו
    1.15
     Etats
    1.04
    ou
    0.98
    jährigen
    0.97
    u
    0.95
     Tết
    0.94
    ু
    0.93
     సంబంధించిన
    0.93
    ো
    0.92
    POSITIVE LOGITS
    ید
    1.30
     ک
    1.13
    ة
    1.05
     aerodynamic
    1.04
     می
    1.02
    0
    1.02
    t
    1.01
    ties
    0.98
    بی
    0.96
     as
    0.95
    Act Density 0.002%

    No Known Activations