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

    Neuronpedia

    INDEX
    Explanations

    How

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _stack
    -0.06
     polygons
    -0.06
     رضا
    -0.06
     rectangle
    -0.05
    trer
    -0.05
    isiert
    -0.05
     nuestras
    -0.05
     Ashton
    -0.05
    雪
    -0.05
     simil
    -0.05
    POSITIVE LOGITS
    ndon
    0.07
    ilog
    0.07
    atio
    0.07
     eksik
    0.07
     Emit
    0.07
     connect
    0.07
    _launch
    0.07
    .Float
    0.06
    immel
    0.06
    alli
    0.06
    Act Density 0.012%

    No Known Activations