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

    Neuronpedia

    INDEX
    Explanations

    formatting strings with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     longitudine
    0.24
    섦
    0.23
     дося
    0.21
     راہ
    0.21
     diá
    0.21
     colère
    0.20
     averiguar
    0.20
     sintomi
    0.20
     speichern
    0.20
    𒄭
    0.20
    POSITIVE LOGITS
    w
    0.20
    old
    0.19
     T
    0.19
     W
    0.18
    ((
    0.18
     Get
    0.17
    ’
    0.17
     ((
    0.17
    new
    0.17
    on
    0.17
    Act Density 0.128%

    No Known Activations