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

    Neuronpedia

    INDEX
    Explanations

    disclaimer, categorized, list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tabel
    0.40
     siano
    0.39
     Associação
    0.39
     Assist
    0.38
     apakah
    0.37
     hayas
    0.37
     storico
    0.37
     monotonic
    0.36
     históricos
    0.36
     histórico
    0.36
    POSITIVE LOGITS
    environment
    0.38
    interesting
    0.35
    his
    0.34
    atmospheric
    0.34
    copper
    0.33
    ทะ
    0.33
    IBM
    0.33
    atoms
    0.32
    Copper
    0.32
    Philadelphia
    0.32
    Act Density 0.667%

    No Known Activations