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

    Neuronpedia

    INDEX
    Explanations

    represent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    落ち
    -0.08
     issue
    -0.07
     di
    -0.07
    Ich
    -0.07
     tinder
    -0.07
    同心
    -0.07
     goto
    -0.07
    .fixed
    -0.07
    logout
    -0.07
    موا
    -0.07
    POSITIVE LOGITS
     represents
    0.09
    representation
    0.09
    랩
    0.08
     represented
    0.08
    Ʀ
    0.08
     Represents
    0.08
     representation
    0.07
     Represent
    0.07
    BigInt
    0.07
    ^K
    0.07
    Act Density 0.049%

    No Known Activations