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

    Neuronpedia

    INDEX
    Explanations

    suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ப்பூ
    0.43
    )-,
    0.42
    asar
    0.40
    ింది
    0.39
    合わせて
    0.39
    etin
    0.39
    UCKY
    0.39
    ádz
    0.38
    Cay
    0.38
    forte
    0.38
    POSITIVE LOGITS
     literally
    0.45
     excesses
    0.42
     doves
    0.41
     niche
    0.41
     however
    0.41
     nothing
    0.40
     However
    0.40
     horses
    0.40
     apost
    0.40
     great
    0.39
    Act Density 0.000%

    No Known Activations