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

    Neuronpedia

    INDEX
    Explanations

    URLs followed by list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Christopher
    0.42
    Vu
    0.37
    othy
    0.36
    pleasant
    0.35
     혼
    0.35
     Vu
    0.35
     Zal
    0.35
    Springer
    0.34
    plein
    0.34
    othic
    0.34
    POSITIVE LOGITS
    DM
    0.40
     कटौती
    0.40
    De
    0.38
    ကား
    0.38
     De
    0.38
    ユ
    0.36
    VY
    0.36
    牟
    0.35
    ئي
    0.34
     DM
    0.34
    Act Density 0.009%

    No Known Activations