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

    Neuronpedia

    INDEX
    Explanations

    code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	pos
    -0.07
    eneg
    -0.06
    ImageContext
    -0.06
     trận
    -0.06
    poses
    -0.06
     tímto
    -0.06
    edium
    -0.06
    enga
    -0.06
     fuer
    -0.06
    imax
    -0.06
    POSITIVE LOGITS
    prepend
    0.06
     Academy
    0.06
    .pred
    0.06
    /todo
    0.06
    .Short
    0.06
    449
    0.06
     Aws
    0.06
     PLC
    0.06
     slack
    0.06
     guide
    0.06
    Act Density 0.000%

    No Known Activations