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

    Neuronpedia

    INDEX
    Explanations

    British

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getModel
    -0.06
     Ideal
    -0.06
    Elim
    -0.06
    \Configuration
    -0.06
    наруж
    -0.06
    imenti
    -0.06
     assassin
    -0.06
    Une
    -0.06
    equiv
    -0.06
    附近
    -0.06
    POSITIVE LOGITS
     British
    0.09
    British
    0.07
     Brit
    0.07
    .b
    0.07
     bf
    0.07
    .middle
    0.07
     bt
    0.07
     robust
    0.06
    castHit
    0.06
     알고
    0.06
    Act Density 0.008%

    No Known Activations