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

    Neuronpedia

    INDEX
    Explanations

    cluster with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bahan
    0.48
     Madre
    0.46
    sill
    0.45
     Wicked
    0.44
    thus
    0.44
    ino
    0.43
    dash
    0.42
    筫
    0.42
    ali
    0.41
    raz
    0.41
    POSITIVE LOGITS
     core
    0.54
    ",
    0.50
    .",
    0.50
     evaluation
    0.49
     использовать
    0.48
     assess
    0.48
     utilização
    0.45
     uč
    0.45
     doenças
    0.45
    ]++;
    0.44
    Act Density 0.000%

    No Known Activations