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

    Neuronpedia

    INDEX
    Explanations

    new beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     แบ่ง
    0.99
     Mirrors
    0.96
    แด
    0.96
    าด
    0.96
    多样
    0.93
     จำ
    0.92
     delineate
    0.90
     מא
    0.89
    스트
    0.89
    罨
    0.88
    POSITIVE LOGITS
    heb
    1.19
    advantage
    1.15
    amazing
    1.14
     humbled
    1.13
    bf
    1.12
    wonderful
    1.09
     marav
    1.09
     aficionados
    1.07
     incumbent
    1.07
    preferred
    1.07
    Act Density 0.000%

    No Known Activations