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

    Neuronpedia

    INDEX
    Explanations

    background colors and corner radii

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ystate
    0.39
    forRoot
    0.38
    iputi
    0.38
     لی
    0.37
     viaj
    0.36
     капи
    0.36
     რომლებიც
    0.36
    र्जा
    0.35
     الحق
    0.35
     conceded
    0.35
    POSITIVE LOGITS
    Paulo
    0.42
    VIN
    0.40
    CIAL
    0.39
    ologia
    0.38
     ureth
    0.38
    printed
    0.37
    cote
    0.37
    wound
    0.37
    BT
    0.37
    ego
    0.37
    Act Density 0.002%

    No Known Activations