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

    Neuronpedia

    INDEX
    Explanations

    here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ):
    0.41
     evacuated
    0.39
     swapped
    0.38
     swaps
    0.38
    SEVERE
    0.38
    gameObjects
    0.38
    Simpson
    0.37
     Kem
    0.36
    Kem
    0.36
     સ્વ
    0.36
    POSITIVE LOGITS
    utant
    0.40
    issense
    0.39
     Authorized
    0.37
     sensitivity
    0.37
    靑
    0.36
    hence
    0.35
     মির
    0.35
    ুক্তি
    0.35
    ServletContext
    0.35
    ▔
    0.35
    Act Density 0.001%

    No Known Activations