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

    Neuronpedia

    INDEX
    Explanations

    rusty key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h3>
    0.61
    ontrol
    0.57
    oda
    0.55
    akes
    0.54
    ift
    0.54
    els
    0.53
    iam
    0.53
    umni
    0.51
    oked
    0.51
    </h5>
    0.50
    POSITIVE LOGITS
    اب
    0.54
    できる
    0.54
    的
    0.54
    ল
    0.51
     resulta
    0.50
    하시
    0.49
    기
    0.48
    인
    0.48
    の
    0.47
    링
    0.46
    Act Density 0.001%

    No Known Activations