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

    Neuronpedia

    INDEX
    Explanations

    UTF-8 charset encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    臀
    0.44
    DIY
    0.38
    chid
    0.38
    ხედ
    0.38
    Scatter
    0.37
    ণ
    0.37
    decrement
    0.37
    onclick
    0.37
    esehen
    0.37
    hAP
    0.36
    POSITIVE LOGITS
     Language
    0.64
     language
    0.64
     jazy
    0.61
     jezik
    0.61
     lingua
    0.57
     लैंग्वेज
    0.55
     utf
    0.54
     languages
    0.54
     Languages
    0.54
     lingue
    0.54
    Act Density 0.032%

    No Known Activations