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

    Neuronpedia

    INDEX
    Explanations

    As sentence start

    np_acts-logits-general · gemini-2.5-flash-lite

    starts with ## or "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.47
    il
    0.41
    ts
    0.41
    ises
    0.39
    ous
    0.38
    ine
    0.38
    ip
    0.38
    ants
    0.37
    ation
    0.36
    ítés
    0.36
    POSITIVE LOGITS
    इंडीज
    0.34
     tzv
    0.34
    হ
    0.33
     Chowdh
    0.33
    τ
    0.33
     comenz
    0.32
    ంద్ర
    0.32
     lanz
    0.32
    σε
    0.32
     cual
    0.32
    Act Density 0.099%

    No Known Activations