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

    Neuronpedia

    INDEX
    Explanations

    code formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MSG
    -0.08
     Filename
    -0.07
     Anonymous
    -0.07
    егодня
    -0.07
     event
    -0.07
     searchable
    -0.07
    /demo
    -0.06
     messenger
    -0.06
    rightarrow
    -0.06
    ilion
    -0.06
    POSITIVE LOGITS
     Axis
    0.07
    _gt
    0.07
    ଉ
    0.07
    (pc
    0.07
    丕
    0.06
    StringUtils
    0.06
    祚
    0.06
     articles
    0.06
    earable
    0.06
    pol
    0.06
    Act Density 0.010%

    No Known Activations