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

    Neuronpedia

    INDEX
    Explanations

    restore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jurisdiction
    -0.07
     wires
    -0.07
    普
    -0.07
    ाइड
    -0.07
     густ
    -0.06
     junction
    -0.06
    venue
    -0.06
    gb
    -0.06
    (pk
    -0.06
    urre
    -0.06
    POSITIVE LOGITS
    _MARKER
    0.06
     respecting
    0.06
    (confirm
    0.06
    Restore
    0.06
     inconvenience
    0.06
    imonial
    0.06
     opatření
    0.06
     memoir
    0.06
    ンティ
    0.06
     MAR
    0.06
    Act Density 0.006%

    No Known Activations