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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    れない
    -0.08
     unlocking
    -0.07
    StartPosition
    -0.07
    不会
    -0.07
     Calories
    -0.06
    ющ
    -0.06
     """
    -0.06
     attends
    -0.06
    Layers
    -0.06
     churches
    -0.06
    POSITIVE LOGITS
     جنگ
    0.06
    <File
    0.06
    .fromFunction
    0.06
    '}↵
    0.06
     매매
    0.06
    (code
    0.06
    ":"/
    0.06
     Paula
    0.06
    ,:,:
    0.06
    циклоп
    0.06
    Act Density 0.025%

    No Known Activations