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

    Neuronpedia

    INDEX
    Explanations

    References

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     valleys
    -0.07
     journalists
    -0.07
     Gir
    -0.06
    Unlock
    -0.06
    .Uri
    -0.06
     ек
    -0.06
     Initi
    -0.06
    .Bean
    -0.06
     curved
    -0.06
     sui
    -0.06
    POSITIVE LOGITS
     ]↵↵
    0.07
     forControlEvents
    0.07
     dicts
    0.06
     overwhelm
    0.06
     end
    0.06
    '].'/
    0.06
    (mu
    0.06
    help
    0.06
    terminated
    0.06
    lime
    0.06
    Act Density 0.002%

    No Known Activations