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

    Neuronpedia

    INDEX
    Explanations

    say "chance"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    realm
    -0.07
     Disc
    -0.07
    oven
    -0.06
     різних
    -0.06
     |_
    -0.06
    專
    -0.06
    Spy
    -0.06
     uit
    -0.06
    000
    -0.06
    FRINGEMENT
    -0.06
    POSITIVE LOGITS
    _extended
    0.07
     soldiers
    0.06
    द
    0.06
    _ability
    0.06
    ,data
    0.06
     Republican
    0.06
     BI
    0.06
    _INET
    0.06
    urrences
    0.06
     nullable
    0.06
    Act Density 0.068%

    No Known Activations