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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (iOS
    -0.07
     Io
    -0.07
    group
    -0.07
    _busy
    -0.07
     mq
    -0.07
     purch
    -0.06
     lacks
    -0.06
    (API
    -0.06
     intents
    -0.06
    -group
    -0.06
    POSITIVE LOGITS
     the
    0.09
    .The
    0.07
    The
    0.07
     THE
    0.07
     The
    0.07
     Fot
    0.07
    席
    0.07
     ACLU
    0.07
    际
    0.06
    цит
    0.06
    Act Density 0.027%

    No Known Activations