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

    Neuronpedia

    INDEX
    Explanations

    asking what you want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಲಾಗಿದೆ
    0.38
     বলিয়
    0.36
    aec
    0.35
    }}$;
    0.34
     अंजाम
    0.33
     potete
    0.33
     getattr
    0.33
     ваше
    0.33
     समझेंगे
    0.33
    க்கப்பட்டது
    0.33
    POSITIVE LOGITS
     muốn
    2.70
     wanting
    2.66
     want
    2.59
     ingin
    2.56
     wanted
    2.41
    想要
    2.36
     wants
    2.31
    want
    2.31
     Want
    2.28
    Want
    2.25
    Act Density 0.168%

    No Known Activations