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

    Neuronpedia

    INDEX
    Explanations

    deck

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     progressive
    -0.08
    India
    -0.08
    סרט
    -0.07
     disrespectful
    -0.07
    Da
    -0.07
    Evidence
    -0.07
    建筑物
    -0.07
     dash
    -0.06
     wedge
    -0.06
    Annotation
    -0.06
    POSITIVE LOGITS
    就不
    0.07
    орм
    0.07
    طلع
    0.07
     braces
    0.07
     voir
    0.07
    弘
    0.07
    致电
    0.07
    ernel
    0.07
    orno
    0.07
    .Parent
    0.07
    Act Density 0.031%

    No Known Activations