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

    Neuronpedia

    INDEX
    Explanations

    OR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ฆ
    -0.08
    �
    -0.07
     elm
    -0.07
    กระเป
    -0.07
    dict
    -0.07
     BTN
    -0.07
     bey
    -0.07
    驰
    -0.07
    Winter
    -0.07
    Reach
    -0.07
    POSITIVE LOGITS
    avs
    0.07
     אפשר
    0.07
    .'.
    0.07
    る
    0.07
    𝔢
    0.07
    uckets
    0.07
     basal
    0.06
    ʌ
    0.06
    的文化
    0.06
     salida
    0.06
    Act Density 0.001%

    No Known Activations