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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     réput
    -0.08
     meets
    -0.07
     precision
    -0.07
     calibrated
    -0.07
     estimates
    -0.07
     gó
    -0.07
     exped
    -0.07
     cautious
    -0.07
     scipy
    -0.07
     Guangdong
    -0.07
    POSITIVE LOGITS
     filhos
    0.11
    内容
    0.11
    _children
    0.10
     콘텐츠
    0.10
     hijos
    0.10
     влож
    0.10
     conteúdo
    0.10
     доч
    0.10
    Children
    0.10
     содерж
    0.10
    Act Density 0.008%

    No Known Activations