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

    Neuronpedia

    INDEX
    Explanations

    signs of contribution or depth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     escrever
    0.51
    Asimismo
    0.47
    ;_
    0.46
    Всім
    0.45
    Foi
    0.45
     theolog
    0.43
    日子
    0.43
    Beverungen
    0.42
    зіно
    0.42
     miejsce
    0.42
    POSITIVE LOGITS
    ouncing
    0.49
    ora
    0.46
     grants
    0.46
    ota
    0.43
    oust
    0.43
    alnya
    0.43
    ers
    0.42
     stai
    0.42
    anced
    0.42
    naires
    0.42
    Act Density 0.003%

    No Known Activations