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

    Neuronpedia

    INDEX
    Explanations

    in the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Around
    0.36
     Homepage
    0.32
    enya
    0.32
    ุม
    0.32
     AVLNode
    0.31
    ısına
    0.31
    Around
    0.31
     planète
    0.31
    '][$
    0.31
    を含む
    0.30
    POSITIVE LOGITS
     midst
    1.13
     vicinity
    0.92
     meantime
    0.87
     guise
    0.79
     wake
    0.75
     absence
    0.73
     context
    0.68
    absence
    0.67
     aftermath
    0.64
     contexto
    0.63
    Act Density 0.057%

    No Known Activations