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

    Neuronpedia

    INDEX
    Explanations

    Social

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elt
    -0.08
     Reyes
    -0.08
     gep
    -0.07
    Knight
    -0.07
     weaponry
    -0.07
    Yu
    -0.07
     Turtle
    -0.07
    uite
    -0.07
    -to
    -0.06
    рут
    -0.06
    POSITIVE LOGITS
     Social
    0.16
     social
    0.16
    social
    0.13
    Social
    0.12
     SOCIAL
    0.12
    /social
    0.10
     Soc
    0.09
     socio
    0.09
    -social
    0.09
    soc
    0.08
    Act Density 0.030%

    No Known Activations