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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    JET
    0.79
     Java
    0.73
     programmers
    0.69
    Java
    0.68
     EFL
    0.68
    cast
    0.68
    MADE
    0.68
     花
    0.67
     উপে
    0.65
     Teflon
    0.65
    POSITIVE LOGITS
     മത്സ
    0.68
     ज़र
    0.62
     Moscou
    0.62
    奶
    0.61
     Munn
    0.60
    ឈ
    0.60
     Conn
    0.60
     sed
    0.59
     crouching
    0.59
     आगाज
    0.59
    Act Density 0.002%

    No Known Activations