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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _feat
    -0.08
    Direccion
    -0.07
     ponds
    -0.07
     vox
    -0.07
    ragments
    -0.06
     preorder
    -0.06
     skull
    -0.06
     kidneys
    -0.06
    .hy
    -0.06
    -wheel
    -0.06
    POSITIVE LOGITS
    ／／
    0.07
    Discuss
    0.07
     tipo
    0.07
     взаим
    0.06
     eins
    0.06
     quân
    0.06
     allen
    0.06
     arada
    0.06
     arab
    0.06
    FFFF
    0.06
    Act Density 0.045%

    No Known Activations