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

    Neuronpedia

    INDEX
    Explanations

    discovers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nů
    -0.07
     Tells
    -0.06
     όλ
    -0.06
     söylem
    -0.06
     balloon
    -0.06
     newX
    -0.06
    Protect
    -0.06
     Bewert
    -0.06
     IPL
    -0.06
     Frozen
    -0.06
    POSITIVE LOGITS
     ironically
    0.07
     linestyle
    0.07
    외
    0.07
     обрат
    0.06
     delivers
    0.06
    jad
    0.06
     reordered
    0.06
     arthritis
    0.06
     Jets
    0.06
    ção
    0.06
    Act Density 0.028%

    No Known Activations