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

    Neuronpedia

    INDEX
    Explanations

    strength rating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aliana
    0.45
     Informations
    0.37
     Pfl
    0.36
     발전
    0.36
     കൊല്ല
    0.36
    iktok
    0.36
    荚
    0.36
     Franz
    0.35
    oursquare
    0.35
     जिल्
    0.34
    POSITIVE LOGITS
     கவனம்
    0.40
     நீண்ட
    0.39
     camel
    0.38
    ак
    0.38
    ளோ
    0.37
     बिर
    0.37
    Notice
    0.37
    மையை
    0.36
    ஈ
    0.36
    最近
    0.35
    Act Density 0.001%

    No Known Activations