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

    Neuronpedia

    INDEX
    Explanations

    Pop

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝜋
    -0.07
     ł
    -0.07
    𝜃
    -0.07
     baş
    -0.07
     접근
    -0.07
    真正
    -0.07
    ҫ
    -0.07
     Bliss
    -0.07
    ElementType
    -0.06
    letic
    -0.06
    POSITIVE LOGITS
    (Card
    0.06
    صم
    0.06
     оригина
    0.06
    捍
    0.06
    ELEMENT
    0.06
    ARING
    0.06
     Berkeley
    0.06
     mount
    0.06
     MOTOR
    0.06
    卓
    0.06
    Act Density 0.001%

    No Known Activations