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

    Neuronpedia

    INDEX
    Explanations

    surveys and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kingdom
    -0.07
    ugin
    -0.06
    ност
    -0.06
    Seg
    -0.06
     FIR
    -0.06
     Ket
    -0.06
     Lite
    -0.06
     Discipline
    -0.06
     Jerusalem
    -0.06
     Allah
    -0.06
    POSITIVE LOGITS
     üy
    0.08
    ینی
    0.07
     lineback
    0.06
    लग
    0.06
    striction
    0.06
     proph
    0.06
    .choices
    0.06
     přem
    0.06
     engaged
    0.06
    _intr
    0.06
    Act Density 0.071%

    No Known Activations