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

    Neuronpedia

    INDEX
    Explanations

    container

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     questioning
    -0.07
    .А
    -0.07
    inke
    -0.06
    ались
    -0.06
    år
    -0.06
     Route
    -0.06
     Radio
    -0.06
     regimen
    -0.06
     standardized
    -0.06
     був
    -0.06
    POSITIVE LOGITS
     pís
    0.06
    	offset
    0.06
    kl
    0.06
    appl
    0.06
     �
    0.06
     geek
    0.06
     пуст
    0.06
     buffers
    0.06
     altında
    0.06
     në
    0.06
    Act Density 0.012%

    No Known Activations