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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swarm
    -0.07
    React
    -0.07
    reward
    -0.06
     AUTHOR
    -0.06
     Canton
    -0.06
     bulundu
    -0.06
    ret
    -0.06
    ("`
    -0.06
     cops
    -0.06
    .dispose
    -0.06
    POSITIVE LOGITS
     Archer
    0.07
    戶
    0.07
     uw
    0.07
    (New
    0.07
     PCS
    0.06
     hypers
    0.06
     Bers
    0.06
     especial
    0.06
     особенно
    0.06
     yok
    0.06
    Act Density 0.000%

    No Known Activations