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

    Neuronpedia

    INDEX
    Explanations

    Illuminate PHP namespace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ne
    1.05
    ni
    0.93
     as
    0.91
    ren
    0.83
     that
    0.82
    ma
    0.81
    nt
    0.80
    จะ
    0.80
    ere
    0.78
    se
    0.77
    POSITIVE LOGITS
    اك
    1.00
    0
    0.96
    ווי
    0.95
    ா
    0.93
    고
    0.91
    ０
    0.90
    ו
    0.88
    ালা
    0.87
    ]
    0.77
    γκ
    0.76
    Act Density 0.001%

    No Known Activations