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

    Neuronpedia

    INDEX
    Explanations

    Studio

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Thought
    -0.07
     disrupt
    -0.07
    ещ
    -0.07
    vio
    -0.07
    ♨
    -0.07
     furnace
    -0.06
    ju
    -0.06
    MI
    -0.06
     ea
    -0.06
    toupper
    -0.06
    POSITIVE LOGITS
    /firebase
    0.07
    {s
    0.07
    最基本
    0.07
    Postal
    0.07
    璠
    0.07
    因为他们
    0.06
     XY
    0.06
    -law
    0.06
    кая
    0.06
     cipher
    0.06
    Act Density 0.002%

    No Known Activations