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

    Neuronpedia

    INDEX
    Explanations

    lack, lost, or distant things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Unlike
    0.52
     Kudos
    0.46
     tipo
    0.46
     Tipo
    0.45
     Size
    0.45
     Ships
    0.44
    洶
    0.43
     SHIPPING
    0.43
     segu
    0.42
     Boats
    0.42
    POSITIVE LOGITS
    리를
    0.48
    ä
    0.46
    velles
    0.46
    ServerSocket
    0.46
    aule
    0.45
    ленні
    0.44
    橥
    0.44
    liche
    0.44
    ələ
    0.44
     ев
    0.43
    Act Density 0.002%

    No Known Activations