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

    Neuronpedia

    INDEX
    Explanations

    DevOps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Robert
    -0.07
    Logger
    -0.07
     beasts
    -0.06
    альная
    -0.06
    rom
    -0.06
     safe
    -0.06
     зокрема
    -0.06
    'R
    -0.06
    	ID
    -0.06
    _timestamp
    -0.06
    POSITIVE LOGITS
    038
    0.06
    lomou
    0.06
     květ
    0.06
     Ku
    0.06
     pname
    0.06
    .ค
    0.06
    xmin
    0.06
    major
    0.06
     salads
    0.05
    ்
    0.05
    Act Density 0.047%

    No Known Activations