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

    Neuronpedia

    INDEX
    Explanations

    plurals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     )↵↵↵↵↵↵↵↵
    -0.09
    ío
    -0.08
    .')↵↵
    -0.08
    panels
    -0.07
     DIR
    -0.07
    利润率
    -0.07
     extradition
    -0.07
    FOR
    -0.07
     Institution
    -0.07
     REGARD
    -0.06
    POSITIVE LOGITS
     마지막
    0.08
     Lawrence
    0.07
    برش
    0.07
    antine
    0.07
    柏林
    0.07
     언제
    0.07
     Ceramic
    0.07
    ritic
    0.07
    ž
    0.07
    Slice
    0.07
    Act Density 0.334%

    No Known Activations