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

    Neuronpedia

    INDEX
    Explanations

    again and another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ذره
    0.99
     rispetto
    0.89
     الحمل
    0.86
     گوئی
    0.85
    )}{(
    0.85
    чала
    0.84
     cầm
    0.82
    แข็ง
    0.82
     LEAR
    0.82
     Adel
    0.82
    POSITIVE LOGITS
    plus
    1.06
    PLUS
    0.99
     combin
    0.96
    combin
    0.95
    Plus
    0.93
    ＋
    0.90
     plus
    0.90
    Absolute
    0.89
     Plus
    0.89
     restantes
    0.89
    Act Density 0.826%

    No Known Activations