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

    Neuronpedia

    INDEX
    Explanations

    explainability and transparency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mansfield
    -0.08
     density
    -0.08
     Mailing
    -0.08
     gült
    -0.07
    欢
    -0.07
    ేశ
    -0.07
     बाँ
    -0.07
     gasp
    -0.07
    (Motion
    -0.07
    多野
    -0.07
    POSITIVE LOGITS
     Explain
    0.14
    Explain
    0.13
     uitleg
    0.13
     explain
    0.12
     transparency
    0.12
     transparencia
    0.12
     explanations
    0.11
     expliquer
    0.11
    説明
    0.11
     объяс
    0.11
    Act Density 0.014%

    No Known Activations