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

    Neuronpedia

    INDEX
    Explanations

    hydration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SafeMath
    -0.56
    =$?
    -0.55
     hydrophilic
    -0.55
    atemala
    -0.54
     onlyOwner
    -0.54
    الصفحه
    -0.51
     stdClass
    -0.51
    IndentedString
    -0.50
     déclar
    -0.50
    ugeot
    -0.50
    POSITIVE LOGITS
    ry
    0.69
    ses
    0.64
    ly
    0.63
    ding
    0.61
    der
    0.59
    ness
    0.59
    sy
    0.59
    sing
    0.59
    mer
    0.59
    sw
    0.58
    Act Density 0.057%

    No Known Activations