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

    Neuronpedia

    INDEX
    Explanations

    website urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    泗
    0.25
    溶液
    0.24
     Parses
    0.23
     Lobkovic
    0.23
     paheli
    0.22
     방정식
    0.22
     혈
    0.21
     +#+
    0.21
    ✏
    0.21
    Investigation
    0.21
    POSITIVE LOGITS
    atual
    0.26
    iegend
    0.26
    altro
    0.25
    ass
    0.25
    atively
    0.24
    anga
    0.24
    至於
    0.24
     detto
    0.24
    менту
    0.23
    stack
    0.23
    Act Density 0.007%

    No Known Activations