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

    Neuronpedia

    INDEX
    Explanations

    questions containing "you" or "如何"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     workings
    -0.09
     кос
    -0.08
    doors
    -0.08
     приготов
    -0.08
     seated
    -0.08
     Hay
    -0.08
    denes
    -0.08
    दम
    -0.08
    quad
    -0.08
    mostly
    -0.08
    POSITIVE LOGITS
     fatigue
    0.09
     stressful
    0.09
     confidentiality
    0.09
     стресс
    0.08
     Qualität
    0.08
     വിശ
    0.08
    避免
    0.08
    Heat
    0.08
    评
    0.08
    ouve
    0.08
    Act Density 0.023%

    No Known Activations