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

    Neuronpedia

    INDEX
    Explanations

    cycles and repetition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Angst
    -0.07
     and
    -0.07
    -0.07
    uki
    -0.07
     î
    -0.07
    #!/
    -0.07
     inventory
    -0.06
     særlig
    -0.06
    和
    -0.06
     rational
    -0.06
    POSITIVE LOGITS
     повтор
    0.14
     restart
    0.13
     restarted
    0.13
     repeating
    0.13
     restarting
    0.13
     Restart
    0.12
     tekrar
    0.12
     വീണ്ടും
    0.12
     ಮತ್ತೆ
    0.12
     আবার
    0.12
    Act Density 0.020%
    No Known Activations