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

    Neuronpedia

    INDEX
    Explanations

    acclaimed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    دث
    -0.07
     Ut
    -0.07
     الخط
    -0.07
     उन
    -0.07
    266
    -0.06
     路
    -0.06
     Mesh
    -0.06
     ζω
    -0.06
     unpredict
    -0.06
    甚
    -0.06
    POSITIVE LOGITS
     acclaimed
    0.37
     acclaim
    0.18
     famed
    0.15
    claimed
    0.12
     revered
    0.11
     renowned
    0.11
     reputed
    0.09
     esteemed
    0.09
    owned
    0.09
     bestselling
    0.08
    Act Density 0.003%

    No Known Activations