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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Boys
    -0.07
    VICES
    -0.06
     stringValue
    -0.06
     wrestler
    -0.06
    “↵↵
    -0.06
    �
    -0.06
    Connected
    -0.06
    children
    -0.06
    有点
    -0.06
     馬
    -0.06
    POSITIVE LOGITS
    レ
    0.07
    476
    0.07
     yapı
    0.06
    Title
    0.06
    491
    0.06
    693
    0.06
    430
    0.06
    ược
    0.06
    �
    0.06
    nutí
    0.06
    Act Density 0.025%

    No Known Activations