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

    Neuronpedia

    INDEX
    Explanations

    divisibility problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Relationships
    -0.08
    ंथ
    -0.08
     Critics
    -0.08
    ukh
    -0.08
     resurgence
    -0.08
     Definitions
    -0.07
    kannt
    -0.07
     pioneers
    -0.07
     Marriage
    -0.07
     Witch
    -0.07
    POSITIVE LOGITS
     inserting
    0.10
    填
    0.09
    _SUFFIX
    0.09
    Replacing
    0.09
    _suffix
    0.09
     ersetzt
    0.09
     inserted
    0.09
     replacing
    0.09
    添
    0.09
     filling
    0.09
    Act Density 0.025%

    No Known Activations