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

    Neuronpedia

    INDEX
    Explanations

    market in 2023

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.63
    a
    0.61
    .
    0.54
    an
    0.49
    )}_
    0.49
     Minuten
    0.48
    _',
    0.48
    辦法
    0.47
    ASN
    0.47
    ik
    0.47
    POSITIVE LOGITS
     gimmick
    0.50
     آخر
    0.46
     highlands
    0.46
     ligation
    0.45
    kę
    0.43
    Issledovatel
    0.41
     highland
    0.41
    Ook
    0.41
    ี่ยน
    0.41
    monotonic
    0.41
    Act Density 0.000%

    No Known Activations