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

    Neuronpedia

    INDEX
    Explanations

    ultimatum or organizations impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >,</
    0.50
    िशनर
    0.46
    icions
    0.45
    icons
    0.44
    menubar
    0.44
     স্বায়
    0.44
    ანს
    0.44
    {}'.
    0.43
    رض
    0.43
    endes
    0.43
    POSITIVE LOGITS
     wartime
    0.46
     இணைப்பு
    0.46
     Edward
    0.45
     Wach
    0.43
     uniforms
    0.42
     E
    0.41
     Bell
    0.41
     pad
    0.40
     Pad
    0.40
     oddly
    0.40
    Act Density 0.002%

    No Known Activations