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

    Neuronpedia

    INDEX
    Explanations

    smooth manifolds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    -1.97
    7
    -1.93
    8
    -1.90
    0
    -1.57
    1
    -1.52
    6
    -1.48
     ");
    -1.34
     follows
    -1.24
     getNombre
    -1.21
     ambayo
    -1.20
    POSITIVE LOGITS
    あなたは
    1.52
    ynchronously
    1.45
     of
    1.40
    堝
    1.40
    שלום
    1.40
    istically
    1.39
    ◆◆
    1.38
     muros
    1.38
    前回の
    1.38
    ――――
    1.38
    Act Density 0.043%

    No Known Activations