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

    Neuronpedia

    INDEX
    Explanations

    itarian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dotycz
    -0.08
     Vr
    -0.08
    mpr
    -0.08
     zach
    -0.08
     dokon
    -0.07
     ligament
    -0.07
     Ryan
    -0.07
     房
    -0.07
    .decode
    -0.07
     jogging
    -0.07
    POSITIVE LOGITS
     tendencies
    0.09
     oppressive
    0.09
    verde
    0.08
     authoritarian
    0.08
     posture
    0.08
    ತ್ತು
    0.08
     tolerated
    0.08
     rikt
    0.08
     режима
    0.08
    政
    0.08
    Act Density 0.010%

    No Known Activations