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

    Neuronpedia

    INDEX
    Explanations

    code algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    750
    -0.08
     اختلاف
    -0.08
    (vars
    -0.08
    _else
    -0.08
    -0.08
    835
    -0.08
    _io
    -0.07
    费用
    -0.07
    ители
    -0.07
    754
    -0.07
    POSITIVE LOGITS
     famiglia
    0.08
     crescente
    0.08
     creë
    0.08
    opleiding
    0.08
     attirer
    0.08
     semakin
    0.08
     voed
    0.08
     famille
    0.08
     onge
    0.08
     Vanguard
    0.07
    Act Density 0.004%
    No Known Activations