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

    Neuronpedia

    INDEX
    Explanations

    Circumventing content policies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unseen
    -0.09
     britann
    -0.08
     �
    -0.08
     Coventry
    -0.08
     银
    -0.07
     entrev
    -0.07
     പ്രശ
    -0.07
     որպես
    -0.07
     igba
    -0.07
     assai
    -0.07
    POSITIVE LOGITS
    掉
    0.10
     reckless
    0.10
     waived
    0.10
     наруш
    0.10
    允
    0.09
     flagr
    0.09
     exemptions
    0.09
     blatant
    0.09
     looph
    0.09
     exemption
    0.09
    Act Density 0.063%

    No Known Activations