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

    Neuronpedia

    INDEX
    Explanations

    house

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lder
    -0.06
     krás
    -0.06
     mlad
    -0.06
    快速
    -0.06
    -radio
    -0.06
     shotgun
    -0.06
    -An
    -0.06
    ิลล
    -0.06
    eyn
    -0.06
     있음
    -0.06
    POSITIVE LOGITS
    238
    0.07
     '',
    0.07
    French
    0.07
    513
    0.07
     hairs
    0.07
    スティ
    0.07
    Aligned
    0.07
    437
    0.07
     eats
    0.07
     backButton
    0.07
    Act Density 0.000%

    No Known Activations