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

    Neuronpedia

    INDEX
    Explanations

    cost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coffin
    -0.07
     rulings
    -0.06
     кноп
    -0.06
     enticing
    -0.06
     Moderator
    -0.06
     helping
    -0.06
     kurulan
    -0.06
     muito
    -0.06
     Sem
    -0.06
     suicide
    -0.06
    POSITIVE LOGITS
    (AdapterView
    0.08
     cloak
    0.07
     VPN
    0.07
    bring
    0.06
     برد
    0.06
    468
    0.06
     COMPLETE
    0.06
    svm
    0.06
    .getResources
    0.06
    uce
    0.06
    Act Density 0.017%

    No Known Activations