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

    Neuronpedia

    INDEX
    Explanations

    refresh rate, Hz

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ėti
    0.47
    არა
    0.45
    ばん
    0.44
    ypass
    0.41
    ENGINE
    0.41
    Pass
    0.40
     passenger
    0.40
    ப்பின்
    0.38
    zoom
    0.37
    quitos
    0.37
    POSITIVE LOGITS
     gaming
    0.60
     Gaming
    0.60
    gaming
    0.58
     Game
    0.54
     Adaptive
    0.53
     Free
    0.52
     frees
    0.52
    Gaming
    0.52
     Games
    0.51
     Variable
    0.51
    Act Density 0.017%

    No Known Activations