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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ning
    -0.07
     Welch
    -0.06
     readability
    -0.06
    Thing
    -0.06
     wk
    -0.06
     neglig
    -0.06
    	Transform
    -0.06
    moth
    -0.06
    ,
    -0.06
    -car
    -0.06
    POSITIVE LOGITS
    Earlier
    0.06
    vanized
    0.06
    aptor
    0.06
     revolves
    0.05
    scribed
    0.05
    Important
    0.05
    ушка
    0.05
    иты
    0.05
    jpg
    0.05
     alternatively
    0.05
    Act Density 0.053%

    No Known Activations