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

    Neuronpedia

    INDEX
    Explanations

    university boards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     docs
    -0.07
    _index
    -0.07
     tension
    -0.07
     sustainability
    -0.07
     think
    -0.07
    Coder
    -0.07
     ',↵
    -0.06
    ühl
    -0.06
     teenagers
    -0.06
    دي
    -0.06
    POSITIVE LOGITS
     تخصص
    0.07
    istické
    0.07
    ख
    0.06
    ájem
    0.06
    �
    0.06
     przez
    0.06
     zvý
    0.06
    Inicio
    0.06
     fwd
    0.06
    lijke
    0.06
    Act Density 0.030%

    No Known Activations