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

    Neuronpedia

    INDEX
    Explanations

    code with variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plug
    -0.07
    _Flag
    -0.07
     assigning
    -0.07
     convert
    -0.06
     marrow
    -0.06
    eter
    -0.06
    *v
    -0.06
     Registry
    -0.06
    _chi
    -0.06
     massage
    -0.06
    POSITIVE LOGITS
    цією
    0.07
     promot
    0.06
     esteem
    0.06
    .....
    0.06
    """↵
    0.06
    ...',
    0.06
    assium
    0.06
    -paced
    0.06
    ของค
    0.06
    Hopefully
    0.06
    Act Density 0.068%

    No Known Activations