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

    Neuronpedia

    INDEX
    Explanations

    equivalent, king, Gelato, editor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thats
    0.43
    ்ட்ட
    0.39
     نصی
    0.39
    प्रदर्शन
    0.38
    艋
    0.37
    undaki
    0.36
    getTransforms
    0.36
    木の
    0.36
    Whats
    0.36
     સે
    0.35
    POSITIVE LOGITS
     équ
    0.41
     SEA
    0.38
    ዘ
    0.37
     submar
    0.37
    %%%
    0.36
     equation
    0.35
     labile
    0.34
    ⣿
    0.34
     stat
    0.34
     rep
    0.34
    Act Density 0.000%

    No Known Activations