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

    Neuronpedia

    INDEX
    Explanations

    social justice, "woke" culture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    perfect
    -0.07
    Evt
    -0.07
    Medium
    -0.06
    ющихся
    -0.06
     love
    -0.06
     Access
    -0.06
     Uploaded
    -0.06
    agn
    -0.06
     ku
    -0.06
     tst
    -0.06
    POSITIVE LOGITS
     zakáz
    0.07
     Shard
    0.07
    SEMB
    0.07
    _EXPR
    0.06
     hombres
    0.06
     گن
    0.06
     мыш
    0.06
    #w
    0.06
    "--
    0.06
     شف
    0.06
    Act Density 0.052%

    No Known Activations