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

    Neuronpedia

    INDEX
    Explanations

    special characters after keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ASS
    0.54
    𝐀
    0.54
     सपने
    0.49
     Licence
    0.46
    ORY
    0.46
     licence
    0.44
    esley
    0.44
    Ý
    0.44
    🛰
    0.44
    An
    0.43
    POSITIVE LOGITS
    ци
    0.57
    со
    0.56
    сед
    0.53
    𝚣
    0.50
     ци
    0.49
    </b>
    0.49
     toit
    0.49
     Со
    0.48
    τερ
    0.47
     culturales
    0.46
    Act Density 0.000%

    No Known Activations