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

    Neuronpedia

    INDEX
    Explanations

    careful response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mapped
    0.46
    Ⅸ
    0.46
    醌
    0.44
     জায়
    0.44
    subprocess
    0.44
    绝对
    0.43
    瘴
    0.42
    ㈡
    0.41
    ಸ್‌
    0.41
    ပိုင်း
    0.41
    POSITIVE LOGITS
     succeeding
    0.41
    Bienvenidos
    0.36
     succeed
    0.35
    レ
    0.34
    徐
    0.34
     frontend
    0.34
    ümer
    0.34
     logic
    0.34
     our
    0.33
     text
    0.33
    Act Density 0.000%

    No Known Activations