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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preventative
    -0.06
     dominated
    -0.06
     над
    -0.06
     opponent
    -0.06
     slightly
    -0.05
    clusions
    -0.05
    방송
    -0.05
     있으며
    -0.05
     Figures
    -0.05
    include
    -0.05
    POSITIVE LOGITS
    .getSeconds
    0.07
     एम
    0.07
    //'
    0.07
    /Web
    0.06
     FormControl
    0.06
    م
    0.06
    .rpm
    0.06
     spre
    0.06
    �数
    0.06
    .getById
    0.06
    Act Density 0.111%

    No Known Activations