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

    Neuronpedia

    INDEX
    Explanations

    positive statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Header
    -0.07
     Spartan
    -0.07
     Bình
    -0.07
    統
    -0.07
     preorder
    -0.07
     Ukra
    -0.07
     بانک
    -0.07
    .Time
    -0.06
    badge
    -0.06
     да
    -0.06
    POSITIVE LOGITS
    rigesimal
    0.06
     machinery
    0.06
     beim
    0.06
     timings
    0.06
    생활
    0.06
     aph
    0.06
     emailed
    0.06
     darauf
    0.05
    _lib
    0.05
     Choosing
    0.05
    Act Density 0.110%

    No Known Activations