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

    Neuronpedia

    INDEX
    Explanations

    finding and remembering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ismuth
    0.41
    cited
    0.39
    inue
    0.38
    дово
    0.36
     berlang
    0.36
     deleteTask
    0.36
     downg
    0.36
     گرو
    0.36
     cited
    0.35
     outbreak
    0.35
    POSITIVE LOGITS
     Remember
    0.50
    Remember
    0.49
    找到
    0.44
    Trans
    0.42
     found
    0.42
     찾
    0.42
     găsit
    0.39
    找到了
    0.39
    ONE
    0.39
    Finding
    0.39
    Act Density 0.000%

    No Known Activations