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

    Neuronpedia

    INDEX
    Explanations

    capsules, tablets, pills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     futhi
    1.10
    ্যার
    1.01
    0.99
     ngok
    0.96
     तौर
    0.95
    <unused2155>
    0.95
    वा
    0.94
     crows
    0.94
    蜴
    0.93
    mainWindow
    0.93
    POSITIVE LOGITS
    िक
    0.95
    ভ
    0.89
    ীয়
    0.84
    ី
    0.84
     suoi
    0.83
    gom
    0.79
    ীয়
    0.78
     pens
    0.78
    どう
    0.77
    決
    0.77
    Act Density 0.032%

    No Known Activations