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

    Neuronpedia

    INDEX
    Explanations

    Neural network code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    чив
    -0.09
     uiterlijk
    -0.09
     steal
    -0.09
    破解
    -0.08
    专项
    -0.08
     cracked
    -0.08
     stealing
    -0.08
     gutter
    -0.08
    Forced
    -0.08
     steals
    -0.08
    POSITIVE LOGITS
     Layers
    0.10
     layers
    0.10
     successive
    0.10
     Layer
    0.10
     progressively
    0.10
     cumulative
    0.09
     Chain
    0.09
     Sequential
    0.09
    layers
    0.09
     succession
    0.09
    Act Density 0.002%

    No Known Activations