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

    Neuronpedia

    INDEX
    Explanations

    right parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     majestic
    -0.08
    族自治
    -0.07
    萨
    -0.07
     Фран
    -0.06
     continuum
    -0.06
    ipo
    -0.06
    <class
    -0.06
     Med
    -0.06
    12
    -0.06
    TEMPLATE
    -0.06
    POSITIVE LOGITS
     départ
    0.07
     risking
    0.07
     ket
    0.06
    ‏
    0.06
    -job
    0.06
    ону
    0.06
    ublic
    0.06
    努力
    0.06
    __':
↵
    0.06
    UpInside
    0.06
    Act Density 0.004%

    No Known Activations