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

    Neuronpedia

    INDEX
    Explanations

    permissions properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minimaal
    -0.09
    лагч
    -0.08
     Thorough
    -0.08
    leng
    -0.08
    М
    -0.07
     thorough
    -0.07
     thoroughly
    -0.07
    invest
    -0.07
    files
    -0.07
    ния
    -0.07
    POSITIVE LOGITS
     پشت
    0.09
     తెలియ
    0.08
     永
    0.08
    永
    0.08
     clutter
    0.08
    ocyt
    0.07
     cornerstone
    0.07
     πά
    0.07
    ెంట
    0.07
     refusal
    0.07
    Act Density 0.000%

    No Known Activations