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

    Neuronpedia

    INDEX
    Explanations

    only memory limitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     programme
    0.38
     planet
    0.38
    输出
    0.38
     Planet
    0.37
     Equilibrium
    0.36
     lateral
    0.36
     Programme
    0.36
     درجه
    0.36
     pneum
    0.36
     outputs
    0.36
    POSITIVE LOGITS
    หน่าย
    0.46
     Бере
    0.42
     warto
    0.40
    ств
    0.40
    ợi
    0.40
    Size
    0.39
    責任
    0.39
    เล็ก
    0.39
     серпня
    0.38
     小学
    0.38
    Act Density 0.000%

    No Known Activations