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

    Neuronpedia

    INDEX
    Explanations

    what you like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rhiz
    0.51
     ry
    0.49
     Ruben
    0.48
     Kir
    0.47
     Kyrgyz
    0.46
     ت
    0.46
     Murray
    0.46
     刘
    0.46
     Silk
    0.45
     poly
    0.45
    POSITIVE LOGITS
    ینگ
    0.52
    Exit
    0.50
    ﺑ
    0.49
     وجہ
    0.49
    arono
    0.47
    这种
    0.46
    लक
    0.46
    ignac
    0.46
    ownic
    0.46
    olic
    0.46
    Act Density 0.000%

    No Known Activations