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

    Neuronpedia

    INDEX
    Explanations

    Erebus planet descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     savvy
    -0.09
     periodista
    -0.08
    Assert
    -0.08
    жым
    -0.08
     schn
    -0.07
    Aware
    -0.07
     clueless
    -0.07
    Obstacle
    -0.07
    Understanding
    -0.07
     businessmen
    -0.07
    POSITIVE LOGITS
     Gaia
    0.09
     পৃথিব
    0.08
     Earth's
    0.08
    atius
    0.07
     undergoing
    0.07
    _beta
    0.07
     libr
    0.07
     neb
    0.07
     flux
    0.07
     undergone
    0.07
    Act Density 0.008%

    No Known Activations