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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scouting
    -0.09
     coloring
    -0.07
    窝
    -0.07
     tracing
    -0.07
    ुरी
    -0.07
     commonly
    -0.07
    -smoking
    -0.07
    ्च
    -0.07
     снять
    -0.07
    Introduction
    -0.07
    POSITIVE LOGITS
     indefinitely
    0.09
     integers
    0.09
     xp
    0.09
    Ints
    0.08
     unlimited
    0.08
    整数
    0.08
     circonstances
    0.08
     XP
    0.08
     bec
    0.08
     ceb
    0.08
    Act Density 0.003%

    No Known Activations