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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vertex
    -0.07
    enz
    -0.06
     Graz
    -0.06
     كل
    -0.06
    .wav
    -0.06
     service
    -0.06
     assets
    -0.06
    ROL
    -0.06
    Vin
    -0.06
    Loan
    -0.06
    POSITIVE LOGITS
     představ
    0.07
     deutschen
    0.07
     culprit
    0.06
     Tomas
    0.06
    ós
    0.06
     Rc
    0.06
    endon
    0.06
     Laos
    0.06
    ...↵↵
    0.06
    ;;↵↵
    0.06
    Act Density 0.011%

    No Known Activations