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

    Neuronpedia

    INDEX
    Explanations

    desire or reaction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ertil
    -0.07
    ocese
    -0.07
     digit
    -0.07
     Firmware
    -0.07
     Wiki
    -0.07
    .device
    -0.06
    /basic
    -0.06
    właściw
    -0.06
     //================================================================
    -0.06
    碏
    -0.06
    POSITIVE LOGITS
    SMART
    0.07
    played
    0.07
     reminders
    0.06
    (rule
    0.06
     chảy
    0.06
    (has
    0.06
    其他玩家
    0.06
    Apis
    0.06
    涌入
    0.06
     lows
    0.06
    Act Density 0.058%

    No Known Activations