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

    Neuronpedia

    INDEX
    Explanations

    git

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hunter
    -0.07
    NUMBER
    -0.07
    flash
    -0.07
     İstanbul
    -0.06
    так
    -0.06
     Whatsapp
    -0.06
    NPC
    -0.06
    Pid
    -0.06
     언
    -0.06
    battery
    -0.06
    POSITIVE LOGITS
    е
    0.07
    й
    0.06
     autres
    0.06
    ��
    0.06
    à
    0.06
    ุร
    0.06
     genus
    0.06
    от
    0.06
     дает
    0.06
    asking
    0.06
    Act Density 0.010%

    No Known Activations