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

    Neuronpedia

    INDEX
    Explanations

    terms ending in ize or ators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     насеље
    0.39
    WebSocket
    0.38
     لینڈ
    0.38
     मरने
    0.38
    "+"|".
    0.36
     Кли
    0.36
    モチーフ
    0.36
    ജി
    0.35
    芃
    0.35
     WebSocket
    0.35
    POSITIVE LOGITS
    áticas
    0.43
    ethical
    0.42
     ethical
    0.41
    liver
    0.39
    df
    0.39
    ilded
    0.39
    chst
    0.39
    isst
    0.39
    ान्य
    0.38
    ueba
    0.38
    Act Density 0.000%

    No Known Activations