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

    Neuronpedia

    INDEX
    Explanations

    logline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obs
    0.39
     пре
    0.38
     n
    0.37
     os
    0.36
    ulp
    0.36
     hence
    0.36
     works
    0.36
     thus
    0.35
     по
    0.35
     age
    0.35
    POSITIVE LOGITS
    <unused2074>
    0.48
    ICIENCY
    0.47
    Cryptography
    0.46
     nhàng
    0.46
    IZATION
    0.45
    withstanding
    0.45
    คัญ
    0.44
    Beau
    0.44
    <unused520>
    0.43
    MENTS
    0.43
    Act Density 0.831%

    No Known Activations