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

    Neuronpedia

    INDEX
    Explanations

    within or on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eclipse
    0.43
    Vet
    0.41
     Vet
    0.40
     Fleur
    0.40
     ------------
    0.40
    CEP
    0.38
    cep
    0.38
     直
    0.38
    Cep
    0.38
     cep
    0.38
    POSITIVE LOGITS
     dilig
    0.41
     playerName
    0.40
     সিদ্ধান্তে
    0.39
    subheader
    0.39
    อาการ
    0.38
    preds
    0.38
    amente
    0.37
    omatic
    0.37
     আকার
    0.37
    નેસ
    0.37
    Act Density 0.000%

    No Known Activations