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

    Neuronpedia

    INDEX
    Explanations

    lie

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ournal
    -0.06
    |#
    -0.06
    amines
    -0.06
    urrect
    -0.06
     antenna
    -0.06
    ngen
    -0.06
    ])+
    -0.06
    ANT
    -0.06
     YYYY
    -0.06
    HAVE
    -0.06
    POSITIVE LOGITS
     lies
    0.10
     lie
    0.10
     nằm
    0.08
     lying
    0.08
     lied
    0.08
     resides
    0.07
     lay
    0.07
     sat
    0.07
    Below
    0.07
     liegt
    0.07
    Act Density 0.014%

    No Known Activations