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

    Neuronpedia

    INDEX
    Explanations

    approximation symbol or word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بیاکتنې
    0.50
    "--
    0.48
    "-"
    0.48
    corsi
    0.47
    "-
    0.44
     excret
    0.44
    翻訳
    0.43
     bepa
    0.43
     identifica
    0.43
     synthesizing
    0.43
    POSITIVE LOGITS
    器的
    0.52
    Plan
    0.49
    计划
    0.49
     Plan
    0.46
    기에
    0.46
    𝐌
    0.45
    న్‌
    0.44
    Chron
    0.44
    자
    0.44
    Min
    0.44
    Act Density 0.000%

    No Known Activations