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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     placed
    -0.07
    unj
    -0.07
    ?.
    -0.07
    emies
    -0.07
    crollView
    -0.07
    rotch
    -0.06
    /events
    -0.06
    \)
    -0.06
    �数
    -0.06
    وني
    -0.06
    POSITIVE LOGITS
    puties
    0.07
     selectors
    0.06
    .xticks
    0.06
     tý
    0.06
    (jj
    0.06
    .unlock
    0.06
     dlouho
    0.06
     batting
    0.06
     Instructions
    0.06
     orth
    0.06
    Act Density 0.001%

    No Known Activations