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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ovalo
    -0.07
    Eye
    -0.06
    (sv
    -0.06
    Colon
    -0.06
    (){↵↵
    -0.06
     tvor
    -0.06
     Merchant
    -0.06
     yani
    -0.06
    струк
    -0.06
    (sz
    -0.06
    POSITIVE LOGITS
     evade
    0.08
     establishments
    0.07
     hrom
    0.07
    ุร
    0.07
    ertime
    0.07
    ải
    0.06
     blank
    0.06
     establishment
    0.06
     BET
    0.06
    imento
    0.06
    Act Density 0.024%

    No Known Activations