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

    Neuronpedia

    INDEX
    Explanations

    improvis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cogn
    -0.07
    dato
    -0.06
     очист
    -0.06
    جد
    -0.06
    消费
    -0.06
     Cargo
    -0.06
     leak
    -0.06
    Công
    -0.06
     �
    -0.06
    .EntityFrameworkCore
    -0.06
    POSITIVE LOGITS
     improvis
    0.09
     improvised
    0.09
     latter
    0.08
    らない
    0.07
    _while
    0.07
    564
    0.07
    velocity
    0.07
    ZY
    0.07
     heck
    0.06
    locale
    0.06
    Act Density 0.003%

    No Known Activations