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

    Neuronpedia

    INDEX
    Explanations

    technical terms itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    銚
    0.43
    瞟
    0.43
    ობს
    0.41
    รู้จัก
    0.41
    umur
    0.41
    𐰞
    0.40
    ൪
    0.40
    ོན་
    0.38
     מספר
    0.38
    <unused323>
    0.38
    POSITIVE LOGITS
     itself
    0.44
     însă
    0.44
     Acids
    0.43
     inoltre
    0.42
     wyłącznie
    0.42
     vogliamo
    0.42
    ளாக
    0.41
     unequivocally
    0.41
     esclusivamente
    0.41
     现在
    0.41
    Act Density 0.016%

    No Known Activations