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

    Neuronpedia

    INDEX
    Explanations

    financial and customer preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shadows
    0.42
     shadow
    0.38
    Shadow
    0.38
     shadowed
    0.38
     Portuguese
    0.37
     shakespeare
    0.36
     Shadow
    0.36
     stoneware
    0.36
     soldier
    0.36
    شك
    0.36
    POSITIVE LOGITS
     ખૂબ
    0.43
    BOOL
    0.40
    oop
    0.39
     Tập
    0.38
     بہت
    0.37
    бы
    0.37
    кі
    0.37
     transposition
    0.37
    чают
    0.37
     نیٹ
    0.37
    Act Density 0.001%

    No Known Activations