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

    Neuronpedia

    INDEX
    Explanations

    say

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     수도
    -0.07
    	dest
    -0.06
     PLAN
    -0.06
     своє
    -0.06
     href
    -0.06
    .rs
    -0.06
    -self
    -0.06
     donation
    -0.06
     dart
    -0.06
    Thanks
    -0.06
    POSITIVE LOGITS
    egasus
    0.06
    Ž
    0.06
    ジ
    0.06
    utdown
    0.06
    Loaded
    0.06
    	ll
    0.06
    配置
    0.06
    ージ
    0.06
    кость
    0.06
    очные
    0.06
    Act Density 0.080%

    No Known Activations