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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    首都
    -0.07
    新华网
    -0.07
     Clim
    -0.07
    shortcut
    -0.07
    .Mask
    -0.07
    victim
    -0.07
    🛁
    -0.07
     oauth
    -0.07
    Advanced
    -0.06
     arrogance
    -0.06
    POSITIVE LOGITS
    女人
    0.07
    ℝ
    0.07
     чувство
    0.07
    让人
    0.07
    UpEdit
    0.07
     critics
    0.07
    					↵					↵
    0.07
    忧
    0.07
    -engine
    0.06
     وي
    0.06
    Act Density 0.005%

    No Known Activations