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

    Neuronpedia

    INDEX
    Explanations

    don't just memorize; understand why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ʕ
    0.55
    i
    0.51
    ni
    0.49
    ens
    0.49
    an
    0.48
    d
    0.46
    V
    0.46
    g
    0.46
    à
    0.46
    ◡
    0.46
    POSITIVE LOGITS
     amaze
    0.53
    இதில்
    0.48
    Analysts
    0.46
    另外
    0.43
    قتصاد
    0.43
     задачи
    0.43
     општи
    0.43
    ير
    0.42
    volvement
    0.42
     economy
    0.42
    Act Density 0.000%

    No Known Activations