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

    Neuronpedia

    INDEX
    Explanations

    availability guess, measured

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    same
    0.45
    but
    0.44
     selben
    0.43
     जोकि
    0.41
     aceea
    0.41
     इन्हीं
    0.40
    但这
    0.40
     ប៉ុ
    0.40
    த்தினை
    0.40
     นั้น
    0.39
    POSITIVE LOGITS
     للد
    0.37
     නම්
    0.37
    指南
    0.37
    禁用
    0.37
     change
    0.36
     nếu
    0.36
     取
    0.36
     Yum
    0.36
     IMS
    0.36
     변경
    0.36
    Act Density 0.008%

    No Known Activations