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

    Neuronpedia

    INDEX
    Explanations

    OS cluster configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जुड़े
    0.31
     δ
    0.27
    Bracelet
    0.24
     करवाए
    0.24
    を使った
    0.23
     undertaken
    0.23
    Rober
    0.22
    াৎ
    0.22
    된
    0.22
     कराए
    0.22
    POSITIVE LOGITS
    ulling
    0.31
    LLING
    0.31
     demás
    0.30
     bunların
    0.29
     newMovie
    0.29
    gares
    0.29
     urgente
    0.28
    nitř
    0.28
    erro
    0.28
    écran
    0.28
    Act Density 0.000%

    No Known Activations