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

    Neuronpedia

    INDEX
    Explanations

    To help me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uing
    1.84
    ㅐ
    1.73
    ầng
    1.72
     bæ
    1.71
    elum
    1.65
     新款
    1.64
    kprop
    1.63
    ㅔ
    1.63
    ㅓ
    1.63
    ﮢ
    1.60
    POSITIVE LOGITS
     contexte
    1.49
     current
    1.37
     que
    1.30
     globo
    1.28
    ട്ര
    1.27
     connaissez
    1.26
     हाल
    1.26
    জ্ঞ
    1.25
     this
    1.23
     limitaciones
    1.22
    Act Density 0.174%

    No Known Activations