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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Selection
    -0.07
    )],
    -0.07
    撰
    -0.06
     Messaging
    -0.06
    TIME
    -0.06
     WARRANTY
    -0.06
    ालय
    -0.06
     залеж
    -0.06
     Amnesty
    -0.06
    -window
    -0.06
    POSITIVE LOGITS
    chyb
    0.07
     hotelu
    0.07
    _Row
    0.07
     이동합니다
    0.06
    anked
    0.06
     spiele
    0.06
    _MSB
    0.06
    されている
    0.06
    _cg
    0.06
     系
    0.06
    Act Density 0.053%

    No Known Activations