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

    Neuronpedia

    INDEX
    Explanations

    in a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    自治
    0.43
     सर
    0.41
    itores
    0.40
    astronaut
    0.38
     Хабаровского
    0.36
    sru
    0.36
    astica
    0.36
    astics
    0.36
    ϕ
    0.36
    pción
    0.35
    POSITIVE LOGITS
    賤
    0.47
     mei
    0.42
     Under
    0.41
    ۈ
    0.40
     Rab
    0.38
     Accum
    0.38
     AGAINST
    0.37
     Làm
    0.36
     J
    0.36
    ാര
    0.36
    Act Density 0.001%

    No Known Activations