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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     аналог
    -0.07
    (크기
    -0.07
    ί
    -0.06
    _FUNCTIONS
    -0.06
     transl
    -0.06
     Fi
    -0.06
     المك
    -0.06
    Exited
    -0.06
     UITableViewController
    -0.06
    aniu
    -0.06
    POSITIVE LOGITS
     braking
    0.07
    redits
    0.07
     sclerosis
    0.07
    ylinder
    0.07
    grily
    0.07
    /simple
    0.07
    utron
    0.07
     churn
    0.06
    emer
    0.06
     pavement
    0.06
    Act Density 0.025%

    No Known Activations