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

    Neuronpedia

    INDEX
    Explanations

    different creative formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oktoberfest
    0.47
     tujuh
    0.46
     outspoken
    0.42
    7
    0.42
    Limite
    0.41
     тобто
    0.41
    主动
    0.41
    <0xB3>
    0.40
     seventy
    0.40
    addPreferredGap
    0.40
    POSITIVE LOGITS
    从而
    0.49
     करोड़
    0.49
    কোন
    0.46
    從
    0.45
    當然
    0.45
     carreteras
    0.44
    ค่ะ
    0.44
     каких
    0.43
    checkFor
    0.43
    Cách
    0.43
    Act Density 0.086%

    No Known Activations