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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unsupported
    -0.07
    supported
    -0.07
    Larry
    -0.07
    meg
    -0.06
     Hãy
    -0.06
    package
    -0.06
     यद
    -0.06
    alignment
    -0.06
     放
    -0.06
    Cou
    -0.06
    POSITIVE LOGITS
     Intr
    0.07
    ّة
    0.06
     state
    0.06
     gruesome
    0.06
     ITER
    0.06
    hb
    0.06
    iant
    0.06
    _COUNT
    0.06
     wise
    0.06
     connect
    0.06
    Act Density 0.047%

    No Known Activations