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

    Neuronpedia

    INDEX
    Explanations

    product specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ล่าสุด
    0.44
     guardianship
    0.41
     яку
    0.40
     lured
    0.40
    schein
    0.39
     mede
    0.39
    を開始
    0.39
     shouting
    0.39
    あなたの
    0.39
    것도
    0.39
    POSITIVE LOGITS
    Pow
    0.47
    ীর্ণ
    0.45
    Specs
    0.45
    is
    0.45
    eyeglasses
    0.45
     Packer
    0.43
    it
    0.43
     returnPacket
    0.43
     see
    0.42
     Там
    0.42
    Act Density 0.001%

    No Known Activations