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

    Neuronpedia

    INDEX
    Explanations

    #include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drown
    -0.07
    för
    -0.07
     قدر
    -0.07
    spe
    -0.06
    	child
    -0.06
     shred
    -0.06
     adjacency
    -0.06
     humanoid
    -0.06
     useRef
    -0.06
    ]:
↵
    -0.06
    POSITIVE LOGITS
    텔
    0.07
     reinforces
    0.06
     Outputs
    0.06
    utc
    0.06
     onUpdate
    0.06
    oola
    0.06
    _CONTAINER
    0.06
     Plants
    0.06
     incentives
    0.06
    brook
    0.05
    Act Density 0.016%

    No Known Activations