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

    Neuronpedia

    INDEX
    Explanations

    feeding birds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     model
    -0.07
    加载
    -0.07
    'acc
    -0.07
     unt
    -0.07
     mùa
    -0.06
     metros
    -0.06
     Hi
    -0.06
    angle
    -0.06
    (val
    -0.06
     ENTER
    -0.06
    POSITIVE LOGITS
    𨚕
    0.07
    ⇔
    0.07
    เอก
    0.07
     Hospitals
    0.07
    蒡
    0.07
    	RT
    0.07
    PRI
    0.07
    פגיעה
    0.07
    ➣
    0.07
    قضا
    0.06
    Act Density 0.006%

    No Known Activations