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

    Neuronpedia

    INDEX
    Explanations

    providing information and clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     here
    0.46
     but
    0.40
     puedes
    0.37
     puoi
    0.36
     when
    0.35
     aquí
    0.35
     voici
    0.34
     see
    0.34
     below
    0.34
     these
    0.34
    POSITIVE LOGITS
    eningkatan
    0.40
    Provide
    0.35
    providing
    0.35
    libat
    0.34
     Provide
    0.34
    ዃ
    0.33
    ufficient
    0.33
    organizzazione
    0.33
    ucidation
    0.32
    大規模
    0.32
    Act Density 0.302%

    No Known Activations