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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    evaluation
    -0.07
     zároveň
    -0.06
     όπου
    -0.06
     corres
    -0.06
     таке
    -0.06
     některých
    -0.06
     yapan
    -0.06
     qp
    -0.06
    time
    -0.06
    Leading
    -0.06
    POSITIVE LOGITS
     Baum
    0.07
     spans
    0.07
    .scss
    0.06
    .drive
    0.06
     coordinated
    0.06
     (<
    0.06
     Wand
    0.06
    (commands
    0.06
    ificates
    0.06
    ander
    0.06
    Act Density 0.105%

    No Known Activations