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

    Neuronpedia

    INDEX
    Explanations

    code comments/separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fort
    -0.07
     centro
    -0.07
     trust
    -0.06
     gameState
    -0.06
     la
    -0.06
     умови
    -0.06
     empres
    -0.06
     long
    -0.06
    commands
    -0.06
    LoginPage
    -0.06
    POSITIVE LOGITS
     peril
    0.07
     advisable
    0.06
    ोक
    0.06
     phiên
    0.06
     envi
    0.06
     drifting
    0.06
     arttır
    0.06
     OpenFileDialog
    0.06
    Elizabeth
    0.06
     bumped
    0.06
    Act Density 0.008%

    No Known Activations