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

    Neuronpedia

    INDEX
    Explanations

    rare genuine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    配
    0.39
    hydrate
    0.38
     Wild
    0.38
    モバイル
    0.38
     वाह
    0.37
     غذ
    0.37
    企業
    0.37
     عقد
    0.37
    飲食
    0.37
    飲料
    0.36
    POSITIVE LOGITS
     briefly
    0.47
     लीप
    0.46
    infodisc
    0.45
    ENSITY
    0.44
    ствовали
    0.43
    کے
    0.42
    న్
    0.41
    ließlich
    0.40
    Якщо
    0.40
    ථ
    0.40
    Act Density 0.000%

    No Known Activations