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

    Neuronpedia

    INDEX
    Explanations

    CT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    害
    -0.07
     oprav
    -0.07
     Parameter
    -0.07
     Jamal
    -0.06
     Wars
    -0.06
     suppress
    -0.06
    imer
    -0.06
    .bindingNavigatorMove
    -0.06
    ANGO
    -0.06
    ترل
    -0.06
    POSITIVE LOGITS
     CT
    0.08
     colon
    0.07
     dct
    0.07
    _PL
    0.06
    _ment
    0.06
     HDMI
    0.06
    xCE
    0.06
     snatch
    0.06
     اي
    0.06
     ct
    0.06
    Act Density 0.003%

    No Known Activations