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

    Neuronpedia

    INDEX
    Explanations

    eras and ages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     axle
    -0.07
    珠
    -0.07
     ammo
    -0.07
     bě
    -0.07
     kidnapped
    -0.07
     diş
    -0.07
     pickup
    -0.07
    írk
    -0.06
     리
    -0.06
    дом
    -0.06
    POSITIVE LOGITS
     intrusive
    0.07
    作
    0.06
    （昭和
    0.06
    .savetxt
    0.06
    Dispatch
    0.06
     motiv
    0.06
    نویس
    0.06
    _arch
    0.06
     Punch
    0.06
     Impro
    0.06
    Act Density 0.064%

    No Known Activations