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

    Neuronpedia

    INDEX
    Explanations

    online

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SER
    -0.07
     줄
    -0.06
     inflicted
    -0.06
     thấp
    -0.06
    лед
    -0.06
    	call
    -0.06
     torso
    -0.06
     phạm
    -0.06
     foe
    -0.06
    雨
    -0.06
    POSITIVE LOGITS
    ΕΣ
    0.07
    ENT
    0.07
     moduleName
    0.07
    альные
    0.06
    compose
    0.06
     joins
    0.06
    APTER
    0.06
     Colomb
    0.06
    next
    0.06
    ЕТ
    0.06
    Act Density 0.000%

    No Known Activations