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

    Neuronpedia

    INDEX
    Explanations

    technical documents/appendices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ाभ
    -0.06
    FileManager
    -0.06
    SAFE
    -0.06
    ORIZED
    -0.06
    IGATION
    -0.06
     feder
    -0.06
     rejected
    -0.06
    Comb
    -0.06
    802
    -0.06
     нар
    -0.06
    POSITIVE LOGITS
    ६
    0.07
    .getResource
    0.06
     ضو
    0.06
     strr
    0.06
     �
    0.06
    hetto
    0.06
    （笑
    0.06
    enda
    0.06
    endum
    0.06
     ανά
    0.06
    Act Density 0.005%

    No Known Activations