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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bilder
    -0.06
     Royal
    -0.06
     presidents
    -0.06
    Royal
    -0.06
     compil
    -0.06
     hunting
    -0.06
    inburgh
    -0.06
     rebellion
    -0.06
    Dyn
    -0.06
     decipher
    -0.06
    POSITIVE LOGITS
    inode
    0.07
    觉得
    0.06
    ≠
    0.06
    ――
    0.06
    ﾍ
    0.06
    PushMatrix
    0.06
     chicas
    0.06
    UED
    0.06
    ',//
    0.06
    ackets
    0.06
    Act Density 0.003%

    No Known Activations