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

    Neuronpedia

    INDEX
    Explanations

    Computer systems and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     furniture
    -0.07
     přep
    -0.07
    -random
    -0.07
     sho
    -0.06
    ？”↵↵
    -0.06
    amaño
    -0.06
     арми
    -0.06
     createContext
    -0.06
     Ross
    -0.06
    enos
    -0.06
    POSITIVE LOGITS
     elev
    0.07
     createdAt
    0.06
     shell
    0.06
    agos
    0.06
    顔を
    0.06
     satellites
    0.06
    ğında
    0.06
    icult
    0.06
     fright
    0.06
     camouflage
    0.06
    Act Density 0.032%

    No Known Activations