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

    Neuronpedia

    INDEX
    Explanations

    Brady

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EUR
    -0.08
     ethanol
    -0.07
     KH
    -0.07
    estone
    -0.07
    ATEGY
    -0.07
     Cornwall
    -0.06
    usters
    -0.06
     techniques
    -0.06
    �
    -0.06
    aksi
    -0.06
    POSITIVE LOGITS
     Brady
    0.17
    ady
    0.09
     Barrett
    0.08
     Riley
    0.07
     bidi
    0.07
     bruises
    0.07
     Bravo
    0.07
    gré
    0.07
     subordinate
    0.06
     Watt
    0.06
    Act Density 0.001%

    No Known Activations