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

    Neuronpedia

    INDEX
    Explanations

    if use return properly develop unlocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ва
    0.48
    ції
    0.46
    who
    0.42
    ум
    0.41
    Ib
    0.41
     ارتباط
    0.40
    нику
    0.40
    uns
    0.40
    UMP
    0.40
    UM
    0.40
    POSITIVE LOGITS
     químico
    0.47
    o
    0.46
    f
    0.46
    )");
    0.46
    aes
    0.45
    bog
    0.45
     productor
    0.45
     serviços
    0.44
     descub
    0.44
     molécule
    0.44
    Act Density 0.000%

    No Known Activations