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

    Neuronpedia

    INDEX
    Explanations

    resistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EXTERNAL
    -0.08
    .Container
    -0.06
     synagogue
    -0.06
    _scripts
    -0.06
    ¼
    -0.06
     Terrace
    -0.06
     regimes
    -0.06
     neighbor
    -0.06
     Голов
    -0.06
    caps
    -0.06
    POSITIVE LOGITS
     وقد
    0.07
    ingredients
    0.07
     Vanessa
    0.07
     кредит
    0.06
              
↵
    0.06
    Or
    0.06
     Erot
    0.06
     touted
    0.06
     وأن
    0.06
    								↵
    0.06
    Act Density 0.129%

    No Known Activations