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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HL
    -0.07
     Hornets
    -0.07
     Tweet
    -0.07
     adaptive
    -0.07
     Montreal
    -0.07
    207
    -0.07
     dyn
    -0.07
     CHAR
    -0.06
    聖
    -0.06
    .GL
    -0.06
    POSITIVE LOGITS
     sollen
    0.07
    /github
    0.07
     svenska
    0.06
     soll
    0.06
    一覧
    0.06
     denial
    0.06
     haben
    0.06
     können
    0.06
    numer
    0.06
    μφωνα
    0.06
    Act Density 0.121%

    No Known Activations