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

    Neuronpedia

    INDEX
    Explanations

    describe visual flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naran
    0.40
     nostri
    0.40
     alternativa
    0.39
     nausea
    0.38
     notre
    0.38
     flames
    0.38
    Personnel
    0.38
     narciss
    0.38
     பட்ட
    0.37
     personnel
    0.37
    POSITIVE LOGITS
    ýv
    0.36
    attice
    0.36
    বাবু
    0.36
     Reinigung
    0.35
    ዥ
    0.35
    Font
    0.35
     Formatting
    0.35
    ">)</
    0.35
    的方向
    0.35
     الهمزه
    0.34
    Act Density 0.006%

    No Known Activations