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

    Neuronpedia

    INDEX
    Explanations

    to chart

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ヤマハ
    0.42
     Couple
    0.40
    𝗦
    0.40
    Ninja
    0.37
    ำ
    0.36
     BorderLayout
    0.36
    商店
    0.35
    Toggle
    0.35
    స్‌
    0.35
    MouseButton
    0.35
    POSITIVE LOGITS
     isot
    0.44
    wc
    0.41
     भन्ने
    0.40
     আৰ
    0.39
     क्वेश्चंस
    0.39
     Stag
    0.38
    wami
    0.38
     कहना
    0.37
    iguo
    0.37
     blevet
    0.36
    Act Density 0.000%

    No Known Activations