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

    Neuronpedia

    INDEX
    Explanations

    recommendations or recommend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    analisi
    1.36
    ebut
    1.36
    Leon
    1.31
    यह
    1.26
    ആ
    1.26
    bersihan
    1.26
     pequeno
    1.25
    razione
    1.24
    isasi
    1.24
    তাহাকে
    1.24
    POSITIVE LOGITS
     完全
    1.61
     其他
    1.56
     跟
    1.43
     以及
    1.42
     而且
    1.40
     同时
    1.31
     接
    1.31
     也
    1.29
     让
    1.28
     套
    1.27
    Act Density 0.026%

    No Known Activations