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

    Neuronpedia

    INDEX
    Explanations

    qualities and characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.39
    </sup>
    0.37
     THIS
    0.36
    )--
    0.36
     X
    0.35
     ή
    0.35
     traditionnel
    0.35
     Elise
    0.35
     Taş
    0.35
     அல்லது
    0.34
    POSITIVE LOGITS
    於
    0.52
    ですが
    0.52
     banget
    0.50
     enough
    0.47
     for
    0.47
     demais
    0.46
    heartedly
    0.46
     tentang
    0.43
    于
    0.43
    のですが
    0.43
    Act Density 0.240%

    No Known Activations