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

    Neuronpedia

    INDEX
    Explanations

    answers and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.49
    <0xBE>
    0.47
    会
    0.46
    á
    0.45
     karena
    0.44
    ø
    0.44
    í
    0.43
    AD
    0.42
     è
    0.41
    Lemma
    0.41
    POSITIVE LOGITS
    ווי
    0.47
    in
    0.46
    드의
    0.46
     chari
    0.44
     اعلان
    0.43
     Bedrooms
    0.42
    kowe
    0.42
     የወ
    0.41
     auster
    0.41
    대의
    0.41
    Act Density 0.168%

    No Known Activations