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

    Neuronpedia

    INDEX
    Explanations

    interface and local components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ména
    0.49
    ieniem
    0.49
    ৎ
    0.47
    ಕೆ
    0.46
    ću
    0.46
    自分の
    0.46
    <unused57>
    0.46
    েরা
    0.46
    శ్
    0.45
    ্নে
    0.45
    POSITIVE LOGITS
     plus
    0.83
     PLUS
    0.73
     together
    0.73
     Plus
    0.73
     which
    0.69
     along
    0.69
     additionally
    0.65
     aswell
    0.65
     therefore
    0.65
     inside
    0.64
    Act Density 0.000%

    No Known Activations